Stewart Cheifet, creator of The Computer Chronicles, dead at 87
46 by spankibalt | 21 comments on Hacker News.
46 by spankibalt | 21 comments on Hacker News.
Wednesday, 31 December 2025
Tuesday, 30 December 2025
Monday, 29 December 2025
Sunday, 28 December 2025
Saturday, 27 December 2025
Friday, 26 December 2025
Thursday, 25 December 2025
New top story on Hacker News: Show HN: Lamp Carousel – DIY kinetic sculpture powered by lamp heat
Show HN: Lamp Carousel – DIY kinetic sculpture powered by lamp heat
5 by Evidlo | 0 comments on Hacker News.
I wanted to share this fun craft activity for the holidays that I've been doing with my family over the last few years. I came up with these while cutting up some cans trying to make an aluminum version of paper spinners. There are a variety of shapes that work, but generally bigger+lighter spinners are better. Also incandescent bulbs are the best, but LEDs work too. They remind me of candle carousels I would see at my grandparents' house during Christmas. Let me know what you think!
5 by Evidlo | 0 comments on Hacker News.
I wanted to share this fun craft activity for the holidays that I've been doing with my family over the last few years. I came up with these while cutting up some cans trying to make an aluminum version of paper spinners. There are a variety of shapes that work, but generally bigger+lighter spinners are better. Also incandescent bulbs are the best, but LEDs work too. They remind me of candle carousels I would see at my grandparents' house during Christmas. Let me know what you think!
Wednesday, 24 December 2025
Tuesday, 23 December 2025
Monday, 22 December 2025
New top story on Hacker News: Flock Exposed Its AI-Powered Cameras to the Internet. We Tracked Ourselves
Flock Exposed Its AI-Powered Cameras to the Internet. We Tracked Ourselves
66 by chaps | 33 comments on Hacker News.
https://ift.tt/BhtxnkH
66 by chaps | 33 comments on Hacker News.
https://ift.tt/BhtxnkH
Sunday, 21 December 2025
Saturday, 20 December 2025
New top story on Hacker News: Show HN: HN Wrapped 2025 - an LLM reviews your year on HN
Show HN: HN Wrapped 2025 - an LLM reviews your year on HN
11 by hubraumhugo | 3 comments on Hacker News.
I was looking for some fun project to play around with the latest Gemini models and ended up building this :) Enter your username and get: - Generated roasts and stats based on your HN activity 2025 - Your personalized HN front page from 2035 (inspired by a recent Show HN [0]) - An xkcd-style comic of your HN persona It uses the latest gemini-3-flash and gemini-3-pro-image (nano banana pro) models, which deliver pretty impressive and funny results. A few examples: - dang: https://ift.tt/0aSAGow - myself: https://ift.tt/Kro1w2L Give it a try and share yours :) Happy holidays! [0] https://ift.tt/KXg9sAS
11 by hubraumhugo | 3 comments on Hacker News.
I was looking for some fun project to play around with the latest Gemini models and ended up building this :) Enter your username and get: - Generated roasts and stats based on your HN activity 2025 - Your personalized HN front page from 2035 (inspired by a recent Show HN [0]) - An xkcd-style comic of your HN persona It uses the latest gemini-3-flash and gemini-3-pro-image (nano banana pro) models, which deliver pretty impressive and funny results. A few examples: - dang: https://ift.tt/0aSAGow - myself: https://ift.tt/Kro1w2L Give it a try and share yours :) Happy holidays! [0] https://ift.tt/KXg9sAS
Friday, 19 December 2025
Thursday, 18 December 2025
New top story on Hacker News: Show HN: Paper2Any – Open tool to generate editable PPTs from research papers
Show HN: Paper2Any – Open tool to generate editable PPTs from research papers
6 by Mey0320 | 0 comments on Hacker News.
Hi HN, We are the OpenDCAI group from Peking University. We built Paper2Any, an open-source tool designed to automate the "Paper to Slides" workflow based on our DataFlow-Agent framework. The Problem: Writing papers is hard, but creating professional architecture diagrams and slides (PPTs) is often more tedious. Most AI tools just generate static images (PNGs) that are impossible to tweak for final publication. The Solution: Paper2Any takes a PDF, text, or sketch as input, understands the research logic, and generates fully editable PPTX (PowerPoint) files and SVGs. We prioritize flexibility and fidelity—allowing you to specify page ranges, switch visual styles, and preserve original assets. How it works: 1. Multimodal Reading: Extracts text and visual elements from the paper. You can now specify page ranges (e.g., Method section only) to focus the context and reduce token usage. 2. Content Understanding: Identifies core contributions and structural logic. 3. PPT Generation: Instead of generating one flat image, it generates independent elements (blocks, arrows, text) with selectable visual styles and organizes them into a slide layout. Links: - Demo: http://dcai-paper2any.cpolar.top/ - Code (DataFlow-Agent): https://ift.tt/rDeyGIR We'd love to hear your feedback on the generation quality and the agent workflow!
6 by Mey0320 | 0 comments on Hacker News.
Hi HN, We are the OpenDCAI group from Peking University. We built Paper2Any, an open-source tool designed to automate the "Paper to Slides" workflow based on our DataFlow-Agent framework. The Problem: Writing papers is hard, but creating professional architecture diagrams and slides (PPTs) is often more tedious. Most AI tools just generate static images (PNGs) that are impossible to tweak for final publication. The Solution: Paper2Any takes a PDF, text, or sketch as input, understands the research logic, and generates fully editable PPTX (PowerPoint) files and SVGs. We prioritize flexibility and fidelity—allowing you to specify page ranges, switch visual styles, and preserve original assets. How it works: 1. Multimodal Reading: Extracts text and visual elements from the paper. You can now specify page ranges (e.g., Method section only) to focus the context and reduce token usage. 2. Content Understanding: Identifies core contributions and structural logic. 3. PPT Generation: Instead of generating one flat image, it generates independent elements (blocks, arrows, text) with selectable visual styles and organizes them into a slide layout. Links: - Demo: http://dcai-paper2any.cpolar.top/ - Code (DataFlow-Agent): https://ift.tt/rDeyGIR We'd love to hear your feedback on the generation quality and the agent workflow!
Wednesday, 17 December 2025
Tuesday, 16 December 2025
Monday, 15 December 2025
Sunday, 14 December 2025
Saturday, 13 December 2025
Friday, 12 December 2025
Thursday, 11 December 2025
New top story on Hacker News: Show HN: SIM – Apache-2.0 n8n alternative
Show HN: SIM – Apache-2.0 n8n alternative
20 by waleedlatif1 | 0 comments on Hacker News.
Hey HN, Waleed here. We're building Sim ( https://sim.ai/ ), an open-source visual editor to build agentic workflows. Repo here: https://ift.tt/nuJwypC . Docs here: https://docs.sim.ai . You can run Sim locally using Docker, with no execution limits or other restrictions. We started building Sim almost a year ago after repeatedly troubleshooting why our agents failed in production. Code-first frameworks felt hard to debug because of implicit control flow, and workflow platforms added more overhead than they removed. We wanted granular control and easy observability without piecing everything together ourselves. We launched Sim [1][2] as a drag-and-drop canvas around 6 months ago. Since then, we've added: - 138 blocks: Slack, GitHub, Linear, Notion, Supabase, SSH, TTS, SFTP, MongoDB, S3, Pinecone, ... - Tool calling with granular control: forced, auto - Agent memory: conversation memory with sliding window support (by last n messages or tokens) - Trace spans: detailed logging and observability for nested workflows and tool calling - Native RAG: upload documents, we chunk, embed with pgvector, and expose vector search to agents - Workflow deployment versioning with rollbacks - MCP support, Human-in-the-loop block - Copilot to build workflows using natural language (just shipped a new version that also acts as a superagent and can call into any of your connected services directly, not just build workflows) Under the hood, the workflow is a DAG with concurrent execution by default. Nodes run as soon as their dependencies (upstream blocks) are satisfied. Loops (for, forEach, while, do-while) and parallel fan-out/join are also first-class primitives. Agent blocks are pass-through to the provider. You pick your model (OpenAI, Anthropic, Gemini, Ollama, vLLM), and and we pass through prompts, tools, and response format directly to the provider API. We normalize response shapes for block interoperability, but we're not adding layers that obscure what's happening. We're currently working on our own MCP server and the ability to deploy workflows as MCP servers. Would love to hear your thoughts and where we should take it next :) [1] https://ift.tt/uF93oWP [2] https://ift.tt/NBbEyAC
20 by waleedlatif1 | 0 comments on Hacker News.
Hey HN, Waleed here. We're building Sim ( https://sim.ai/ ), an open-source visual editor to build agentic workflows. Repo here: https://ift.tt/nuJwypC . Docs here: https://docs.sim.ai . You can run Sim locally using Docker, with no execution limits or other restrictions. We started building Sim almost a year ago after repeatedly troubleshooting why our agents failed in production. Code-first frameworks felt hard to debug because of implicit control flow, and workflow platforms added more overhead than they removed. We wanted granular control and easy observability without piecing everything together ourselves. We launched Sim [1][2] as a drag-and-drop canvas around 6 months ago. Since then, we've added: - 138 blocks: Slack, GitHub, Linear, Notion, Supabase, SSH, TTS, SFTP, MongoDB, S3, Pinecone, ... - Tool calling with granular control: forced, auto - Agent memory: conversation memory with sliding window support (by last n messages or tokens) - Trace spans: detailed logging and observability for nested workflows and tool calling - Native RAG: upload documents, we chunk, embed with pgvector, and expose vector search to agents - Workflow deployment versioning with rollbacks - MCP support, Human-in-the-loop block - Copilot to build workflows using natural language (just shipped a new version that also acts as a superagent and can call into any of your connected services directly, not just build workflows) Under the hood, the workflow is a DAG with concurrent execution by default. Nodes run as soon as their dependencies (upstream blocks) are satisfied. Loops (for, forEach, while, do-while) and parallel fan-out/join are also first-class primitives. Agent blocks are pass-through to the provider. You pick your model (OpenAI, Anthropic, Gemini, Ollama, vLLM), and and we pass through prompts, tools, and response format directly to the provider API. We normalize response shapes for block interoperability, but we're not adding layers that obscure what's happening. We're currently working on our own MCP server and the ability to deploy workflows as MCP servers. Would love to hear your thoughts and where we should take it next :) [1] https://ift.tt/uF93oWP [2] https://ift.tt/NBbEyAC
Wednesday, 10 December 2025
New top story on Hacker News: Show HN: Automated license plate reader coverage in the USA
Show HN: Automated license plate reader coverage in the USA
4 by sodality2 | 1 comments on Hacker News.
Built this over the last few days, based on a Rust codebase that parses the latest ALPR reports from OpenStreetMaps, calculates navigation statistics from every tagged residential building to nearby amenities, and tests each route for intersection with those ALPR cameras (Flock being the most widespread). These have gotten more controversial in recent months, due to their indiscriminate large scale data collection, with 404 Media publishing many original pieces ( https://ift.tt/suIFdBU ) about their adoption and (ab)use across the country. I wanted to use open source datasets to track the rapid expansion, especially per-county, as this data can be crucial for 'deflock' movements to petition counties and city governments to ban and remove them. In some counties, the tracking becomes so widespread that most people can't go anywhere without being photographed. This includes possibly sensitive areas, like places of worship and medical facilities. The argument for their legality rests upon the notion that these cameras are equivalent to 'mere observation', but the enormous scope and data sharing agreements in place to share and access millions of records without warrants blurs the lines of the fourth amendment.
4 by sodality2 | 1 comments on Hacker News.
Built this over the last few days, based on a Rust codebase that parses the latest ALPR reports from OpenStreetMaps, calculates navigation statistics from every tagged residential building to nearby amenities, and tests each route for intersection with those ALPR cameras (Flock being the most widespread). These have gotten more controversial in recent months, due to their indiscriminate large scale data collection, with 404 Media publishing many original pieces ( https://ift.tt/suIFdBU ) about their adoption and (ab)use across the country. I wanted to use open source datasets to track the rapid expansion, especially per-county, as this data can be crucial for 'deflock' movements to petition counties and city governments to ban and remove them. In some counties, the tracking becomes so widespread that most people can't go anywhere without being photographed. This includes possibly sensitive areas, like places of worship and medical facilities. The argument for their legality rests upon the notion that these cameras are equivalent to 'mere observation', but the enormous scope and data sharing agreements in place to share and access millions of records without warrants blurs the lines of the fourth amendment.
Tuesday, 9 December 2025
New top story on Hacker News: "The Matilda Effect": Pioneering Women Scientists Written Out of Science History
"The Matilda Effect": Pioneering Women Scientists Written Out of Science History
30 by binning | 3 comments on Hacker News.
30 by binning | 3 comments on Hacker News.
Monday, 8 December 2025
Sunday, 7 December 2025
Saturday, 6 December 2025
Friday, 5 December 2025
Thursday, 4 December 2025
New top story on Hacker News: PyTogether: Collaborative lightweight real-time Python IDE for teachers/learners
PyTogether: Collaborative lightweight real-time Python IDE for teachers/learners
4 by indigodaddy | 0 comments on Hacker News.
4 by indigodaddy | 0 comments on Hacker News.
Wednesday, 3 December 2025
Tuesday, 2 December 2025
Monday, 1 December 2025
Sunday, 30 November 2025
Saturday, 29 November 2025
Friday, 28 November 2025
Thursday, 27 November 2025
Wednesday, 26 November 2025
Tuesday, 25 November 2025
Monday, 24 November 2025
Sunday, 23 November 2025
Saturday, 22 November 2025
Friday, 21 November 2025
Thursday, 20 November 2025
Wednesday, 19 November 2025
New top story on Hacker News: Show HN: Vibe Prolog
Show HN: Vibe Prolog
10 by nl | 0 comments on Hacker News.
Like a lot of people I got the $250 Claude Code credit and didn't use it up. I decided to try to use it up over the weekend using (mostly) my phone and vibe coded a Prolog interpreter. Now I'm seeing how far I can push it.
10 by nl | 0 comments on Hacker News.
Like a lot of people I got the $250 Claude Code credit and didn't use it up. I decided to try to use it up over the weekend using (mostly) my phone and vibe coded a Prolog interpreter. Now I'm seeing how far I can push it.
Tuesday, 18 November 2025
Monday, 17 November 2025
Sunday, 16 November 2025
Saturday, 15 November 2025
Friday, 14 November 2025
Thursday, 13 November 2025
New top story on Hacker News: Ask HN: Anyone else disillusioned with "AI experts" in their team?
Ask HN: Anyone else disillusioned with "AI experts" in their team?
21 by randomgermanguy | 26 comments on Hacker News.
We had an internal-workshop led by our internal AI-team (mostly just LLMs), and had the horrible realisation that no one in that team actually knows what the term "AI" even means, or how a language model works. One senior-dev (team-lead also) tried to explain to me that AI is a subfield of machine-learning, and always stochastic in nature (since ChatGPT responds differently to the same prompt). We/they are selling tailor-made "AI-products" to other businesses, but apparently we don't know how sampling works...? Also, no one could tell me where exactly our "self-hosted" models even ran (turns out 50% of the time its just OpenAI/Anthropic), or what OCR-model our product was using. Am I just too junior/naive to get this or am I cooked?
21 by randomgermanguy | 26 comments on Hacker News.
We had an internal-workshop led by our internal AI-team (mostly just LLMs), and had the horrible realisation that no one in that team actually knows what the term "AI" even means, or how a language model works. One senior-dev (team-lead also) tried to explain to me that AI is a subfield of machine-learning, and always stochastic in nature (since ChatGPT responds differently to the same prompt). We/they are selling tailor-made "AI-products" to other businesses, but apparently we don't know how sampling works...? Also, no one could tell me where exactly our "self-hosted" models even ran (turns out 50% of the time its just OpenAI/Anthropic), or what OCR-model our product was using. Am I just too junior/naive to get this or am I cooked?
Wednesday, 12 November 2025
Tuesday, 11 November 2025
Monday, 10 November 2025
Sunday, 9 November 2025
Saturday, 8 November 2025
Friday, 7 November 2025
Thursday, 6 November 2025
Wednesday, 5 November 2025
Tuesday, 4 November 2025
Sunday, 2 November 2025
Saturday, 1 November 2025
Friday, 31 October 2025
Thursday, 30 October 2025
Wednesday, 29 October 2025
Tuesday, 28 October 2025
New top story on Hacker News: Subvocalization: Toward Hearing the Inner Thoughts of Developers (2011) [pdf]
Subvocalization: Toward Hearing the Inner Thoughts of Developers (2011) [pdf]
11 by faqriansyah | 1 comments on Hacker News.
11 by faqriansyah | 1 comments on Hacker News.
Monday, 27 October 2025
Sunday, 26 October 2025
Saturday, 25 October 2025
Friday, 24 October 2025
Thursday, 23 October 2025
Wednesday, 22 October 2025
Tuesday, 21 October 2025
Monday, 20 October 2025
Sunday, 19 October 2025
New top story on Hacker News: Could the XZ backdoor been detected with better Git/Deb packaging practices?
Could the XZ backdoor been detected with better Git/Deb packaging practices?
12 by ottoke | 2 comments on Hacker News.
12 by ottoke | 2 comments on Hacker News.
Saturday, 18 October 2025
Friday, 17 October 2025
New top story on Hacker News: Show HN: We packaged an MCP server inside Chromium
Show HN: We packaged an MCP server inside Chromium
9 by felarof | 6 comments on Hacker News.
Hey HN, we just shipped a browser with an inbuilt MCP server! We're a YC startup (S24) building BrowserOS — an open‑source Chromium fork. We're a privacy‑first alternative to the new wave of AI browsers like Dia, Perplexity Comet. Since launching ~3 months ago, the #1 request has been to expose our browser as an MCP server. -- Google beat us to launch with chrome-devtools-mcp (solid product btw), which lets you build/debug web apps by connecting Chrome to coding assistants. But we wanted to take this a step further: we packaged the MCP server directly into our browser binary. That gives three advantages: 1. MCP server setup is super simple — no npx install, no starting Chrome with CDP flags, you just download the BrowserOS binary. 2. with our browser's inbuilt MCP server, AI agents can interact using your logged‑in sessions (unlike chrome-devtools-mcp which starts a fresh headless instance each time) 3. our MCP server also exposes new APIs from Chromium's C++ core to click, type, and draw bounding boxes on a webpage. Our APIs are also not CDP-based (Chrome Debug Protocol) and have robust anti-bot detection. -- Few example use cases for BrowserOS-mcp are: a) *Frontend development with Claude Code*: instead of screenshot‑pasting, claude-code gets WYSIWYG access. It can write code, take a screenshot, check console logs, and fix issues in one agentic sweep. Since it has your sessions, it can do QA stuff like "test the auth flow with my Google Sign‑In." Here's a video of claude-code using browserOS to improve the css styling with back-and-forth checking: https://youtu.be/vcSxzIIkg_0 b) *Use as an agentic browser:* You can install BrowserOS-mcp in claude-code or Claude Desktop and do things like form-filling, extraction, multi-step agentic tasks, etc. It honestly works better than Perplexity Comet! Here's a video of claude-code opening top 5 hacker news posts and summarizing: https://youtu.be/rPFx_Btajj0 -- *How we packaged MCP server inside Chromium binary*: We package the server as a Bun binary and expose MCP tools over HTTP instead of stdio (to support multiple sessions). And we have a BrowserOS controller installed as an extension at the application layer which the MCP server connects to over WebSocket to control the browser. Here's a rough architecture diagram: https://dub.sh/browseros-mcp-diag -- *How to install and use it:* We put together a short guide here: https://ift.tt/yZqgDK7 Our vision is to reimagine the browser as an operating system for AI agents, and packaging an MCP server directly into it is a big unlock for that! I'll be hanging around all day, would love to get your feedback and answer any questions!
9 by felarof | 6 comments on Hacker News.
Hey HN, we just shipped a browser with an inbuilt MCP server! We're a YC startup (S24) building BrowserOS — an open‑source Chromium fork. We're a privacy‑first alternative to the new wave of AI browsers like Dia, Perplexity Comet. Since launching ~3 months ago, the #1 request has been to expose our browser as an MCP server. -- Google beat us to launch with chrome-devtools-mcp (solid product btw), which lets you build/debug web apps by connecting Chrome to coding assistants. But we wanted to take this a step further: we packaged the MCP server directly into our browser binary. That gives three advantages: 1. MCP server setup is super simple — no npx install, no starting Chrome with CDP flags, you just download the BrowserOS binary. 2. with our browser's inbuilt MCP server, AI agents can interact using your logged‑in sessions (unlike chrome-devtools-mcp which starts a fresh headless instance each time) 3. our MCP server also exposes new APIs from Chromium's C++ core to click, type, and draw bounding boxes on a webpage. Our APIs are also not CDP-based (Chrome Debug Protocol) and have robust anti-bot detection. -- Few example use cases for BrowserOS-mcp are: a) *Frontend development with Claude Code*: instead of screenshot‑pasting, claude-code gets WYSIWYG access. It can write code, take a screenshot, check console logs, and fix issues in one agentic sweep. Since it has your sessions, it can do QA stuff like "test the auth flow with my Google Sign‑In." Here's a video of claude-code using browserOS to improve the css styling with back-and-forth checking: https://youtu.be/vcSxzIIkg_0 b) *Use as an agentic browser:* You can install BrowserOS-mcp in claude-code or Claude Desktop and do things like form-filling, extraction, multi-step agentic tasks, etc. It honestly works better than Perplexity Comet! Here's a video of claude-code opening top 5 hacker news posts and summarizing: https://youtu.be/rPFx_Btajj0 -- *How we packaged MCP server inside Chromium binary*: We package the server as a Bun binary and expose MCP tools over HTTP instead of stdio (to support multiple sessions). And we have a BrowserOS controller installed as an extension at the application layer which the MCP server connects to over WebSocket to control the browser. Here's a rough architecture diagram: https://dub.sh/browseros-mcp-diag -- *How to install and use it:* We put together a short guide here: https://ift.tt/yZqgDK7 Our vision is to reimagine the browser as an operating system for AI agents, and packaging an MCP server directly into it is a big unlock for that! I'll be hanging around all day, would love to get your feedback and answer any questions!
Thursday, 16 October 2025
Wednesday, 15 October 2025
Tuesday, 14 October 2025
Monday, 13 October 2025
Sunday, 12 October 2025
Saturday, 11 October 2025
Friday, 10 October 2025
New top story on Hacker News: Toyota aims to launch the ' first' all-solid-state EV batteries
Toyota aims to launch the ' first' all-solid-state EV batteries
21 by thelastgallon | 9 comments on Hacker News.
21 by thelastgallon | 9 comments on Hacker News.
New top story on Hacker News: Show HN: Modeling the Human Body in Rust So I Can Cmd+Click Through It
Show HN: Modeling the Human Body in Rust So I Can Cmd+Click Through It
31 by lleong1618 | 33 comments on Hacker News.
I started this trying to understand two things: why my Asian friends turn red after drinking, and why several friends all seemed to have migraine clusters. I was reading medical papers and textbooks, but kept getting lost jumping between topics. I thought: what if I could just Cmd+Click through this like code? What if "ALDH2 gene" was actually clickable, and took me to the variant, the phenotype, the population frequencies? So I started modeling human biology in Rust with my Ralph agent (Claude in a loop, ty ghuntley). Turns out the type system is perfect for this. Every biological entity is strongly-typed with relationships enforced at compile time. After 1 day of agent coding: - 277 Rust files, ~95k lines of code - 1,561 tests passing - 13 complete organ systems - Genetics with ancestry-specific variants - Clinical pathology models Try it: git clone https://ift.tt/rPdzbRt cd open_human_ontology cargo run --example ide_navigation_demo Then open `examples/ide_navigation_demo.rs` and Cmd+Click through: Understanding Asian flush: AsianGeneticVariantsCatalog::get_metabolic_variants() // Click through to: // → ALDH2 gene on chromosome 12q24.12 // → rs671 variant (Glu504Lys) // → 40% frequency in Japanese population // → Alcohol flush reaction // → 10x esophageal cancer risk with alcohol // → Acetaldehyde metabolism pathway Understanding migraines: Migraine { subtype: WithAura, triggers: [Stress, LackOfSleep, HormonalChanges], genetic_variants: ["rs2075968", "rs1835740"], ... } // Click through to: // → 17 migraine trigger types // → 12 aura symptom types // → Genetic risk factors // → Why clusters happen (HormonalChanges → Menstruation) Now I can actually navigate the connections instead of flipping through PDFs. Heart → CoronaryArtery → Plaque. VisualCortex → 200M neurons → NeuralConnection pathways. It's like Wikipedia but type-checked and with jump-to-definition. This isn't production medical software - it's a learning tool. But it's way more useful than textbooks for understanding how biological systems connect. The agent keeps expanding it. Sometimes it OOMs but that's part of the fun. Tech: Rust, nalgebra, serde, rayon, proptest I am not a dr or medical professional this is for my education you can commit to it if you want to or review and open some PR's if you find wrong information or want to add references.
31 by lleong1618 | 33 comments on Hacker News.
I started this trying to understand two things: why my Asian friends turn red after drinking, and why several friends all seemed to have migraine clusters. I was reading medical papers and textbooks, but kept getting lost jumping between topics. I thought: what if I could just Cmd+Click through this like code? What if "ALDH2 gene" was actually clickable, and took me to the variant, the phenotype, the population frequencies? So I started modeling human biology in Rust with my Ralph agent (Claude in a loop, ty ghuntley). Turns out the type system is perfect for this. Every biological entity is strongly-typed with relationships enforced at compile time. After 1 day of agent coding: - 277 Rust files, ~95k lines of code - 1,561 tests passing - 13 complete organ systems - Genetics with ancestry-specific variants - Clinical pathology models Try it: git clone https://ift.tt/rPdzbRt cd open_human_ontology cargo run --example ide_navigation_demo Then open `examples/ide_navigation_demo.rs` and Cmd+Click through: Understanding Asian flush: AsianGeneticVariantsCatalog::get_metabolic_variants() // Click through to: // → ALDH2 gene on chromosome 12q24.12 // → rs671 variant (Glu504Lys) // → 40% frequency in Japanese population // → Alcohol flush reaction // → 10x esophageal cancer risk with alcohol // → Acetaldehyde metabolism pathway Understanding migraines: Migraine { subtype: WithAura, triggers: [Stress, LackOfSleep, HormonalChanges], genetic_variants: ["rs2075968", "rs1835740"], ... } // Click through to: // → 17 migraine trigger types // → 12 aura symptom types // → Genetic risk factors // → Why clusters happen (HormonalChanges → Menstruation) Now I can actually navigate the connections instead of flipping through PDFs. Heart → CoronaryArtery → Plaque. VisualCortex → 200M neurons → NeuralConnection pathways. It's like Wikipedia but type-checked and with jump-to-definition. This isn't production medical software - it's a learning tool. But it's way more useful than textbooks for understanding how biological systems connect. The agent keeps expanding it. Sometimes it OOMs but that's part of the fun. Tech: Rust, nalgebra, serde, rayon, proptest I am not a dr or medical professional this is for my education you can commit to it if you want to or review and open some PR's if you find wrong information or want to add references.
Thursday, 9 October 2025
Wednesday, 8 October 2025
New top story on Hacker News: Show HN: I built a local-first podcast app
Show HN: I built a local-first podcast app
15 by aegrumet | 4 comments on Hacker News.
I worked on early podcast software in 2004 (iPodder/Juice) and have been a heavy podcast consumer ever since. I wanted a podcast app that respects your privacy and embraces the open web—and to explore what's possible in the browser. The result is wherever.audio, which you can try right now at the link above. How it works: It's a progressive web app that stores all your subscriptions and data locally in your browser using IndexedDB. Add it to your home screen and it feels native. Works offline with downloaded episodes. No central server storing your data—just some Cloudflare/AWS helpers to smooth out browser limitations. What makes it different: - True local-first: Your data stays on your device - Custom feeds: Add any RSS feed, not just what's in a directory - On-device search: Search across all feeds and episodes, including your custom ones - Podcasting 2.0 support: Chapters, transcripts, funding tags, and others - Auto-generated chapters: For popular shows that don't have them - AI-powered discovery: Ask questions to find shows and episodes (this feature does send queries to a 3rd party API, and also uses anonymized analytics while we work out the prompts) - Audio-guided tutorials: Interactive walkthroughs with voice guidance and visual cues The basics work well too: Standard playback features, queue management, speed controls, etc. I'm really interested in feedback—this is more passion project than business right now. I've been dogfooding it as my daily podcast app for over a year, and I'm open to exploring making it a business if people find it valuable. Curious if there are unmet needs that a privacy-focused, open web approach could address.
15 by aegrumet | 4 comments on Hacker News.
I worked on early podcast software in 2004 (iPodder/Juice) and have been a heavy podcast consumer ever since. I wanted a podcast app that respects your privacy and embraces the open web—and to explore what's possible in the browser. The result is wherever.audio, which you can try right now at the link above. How it works: It's a progressive web app that stores all your subscriptions and data locally in your browser using IndexedDB. Add it to your home screen and it feels native. Works offline with downloaded episodes. No central server storing your data—just some Cloudflare/AWS helpers to smooth out browser limitations. What makes it different: - True local-first: Your data stays on your device - Custom feeds: Add any RSS feed, not just what's in a directory - On-device search: Search across all feeds and episodes, including your custom ones - Podcasting 2.0 support: Chapters, transcripts, funding tags, and others - Auto-generated chapters: For popular shows that don't have them - AI-powered discovery: Ask questions to find shows and episodes (this feature does send queries to a 3rd party API, and also uses anonymized analytics while we work out the prompts) - Audio-guided tutorials: Interactive walkthroughs with voice guidance and visual cues The basics work well too: Standard playback features, queue management, speed controls, etc. I'm really interested in feedback—this is more passion project than business right now. I've been dogfooding it as my daily podcast app for over a year, and I'm open to exploring making it a business if people find it valuable. Curious if there are unmet needs that a privacy-focused, open web approach could address.
Tuesday, 7 October 2025
New top story on Hacker News: ICE bought vehicles equipped with fake cell towers to spy on phones
ICE bought vehicles equipped with fake cell towers to spy on phones
44 by mdhb | 17 comments on Hacker News.
44 by mdhb | 17 comments on Hacker News.
Monday, 6 October 2025
New top story on Hacker News: Show HN: I've build a platform for writing technical/scientific documents
Show HN: I've build a platform for writing technical/scientific documents
7 by WolfOliver | 2 comments on Hacker News.
7 by WolfOliver | 2 comments on Hacker News.
Sunday, 5 October 2025
New top story on Hacker News: Show HN: ut – Rust based CLI utilities for devs and IT
Show HN: ut – Rust based CLI utilities for devs and IT
20 by ksdme9 | 5 comments on Hacker News.
Hey HN, I find myself reaching for tools like it-tools.tech or other random sites every now and then during development or debugging. So, I built a toolkit with a sane and simple CLI interface for most of those tools. For the curious and lazy, at the moment, ut has tools for, - Encoding: base64 (encode, decode), url (encode, decode) - Hashing: md5, sha1, sha224, sha256, sha384, sha512 - Data Generation: uuid (v1, v3, v4, v5), token, lorem, random - Text Processing: case (lower, upper, camel, title, constant, header, sentence, snake), pretty-print, diff - Development Tools: calc, json (builder), regex, datetime - Web & Network: http (status), serve, qr - Color & Design: color (convert) - Reference: unicode For full disclosure, parts of the toolkit were built with Claude Code (I wanted to use this as an opportunity to play with it more). Feel free to open feature requests and/or contribute.
20 by ksdme9 | 5 comments on Hacker News.
Hey HN, I find myself reaching for tools like it-tools.tech or other random sites every now and then during development or debugging. So, I built a toolkit with a sane and simple CLI interface for most of those tools. For the curious and lazy, at the moment, ut has tools for, - Encoding: base64 (encode, decode), url (encode, decode) - Hashing: md5, sha1, sha224, sha256, sha384, sha512 - Data Generation: uuid (v1, v3, v4, v5), token, lorem, random - Text Processing: case (lower, upper, camel, title, constant, header, sentence, snake), pretty-print, diff - Development Tools: calc, json (builder), regex, datetime - Web & Network: http (status), serve, qr - Color & Design: color (convert) - Reference: unicode For full disclosure, parts of the toolkit were built with Claude Code (I wanted to use this as an opportunity to play with it more). Feel free to open feature requests and/or contribute.
Saturday, 4 October 2025
New top story on Hacker News: Show HN: Run – a CLI universal code runner I built while learning Rust
Show HN: Run – a CLI universal code runner I built while learning Rust
4 by esubaalew | 0 comments on Hacker News.
Hi HN — I’m learning Rust and decided to build a universal CLI for running code in many languages. The tool, Run, aims to be a single, minimal dependency utility for: running one-off snippets (from CLI flags), running files, reading and executing piped stdin, and providing language-specific REPLs that you can switch between interactively. I designed it to support both interpreted languages (Python, JS, Ruby, etc.) and compiled languages (Rust, Go, C/C++). It detects languages from flags or file extensions, can compile temporary files for compiled languages, and exposes a unified REPL experience with commands like :help, :lang, and :quit. Install: cargo install run-kit (or use the platform downloads on GitHub). Source & releases: https://ift.tt/Jw5k2yW I used Rust while following the official learning resources and used AI to speed up development, so I expect there are bugs and rough edges. I’d love feedback on: usability and UX of the REPL, edge cases for piping input to language runtimes, security considerations (sandboxing/resource limits), packaging and cross-platform distribution. Thanks — I’ll try to answer questions and share design notes.
4 by esubaalew | 0 comments on Hacker News.
Hi HN — I’m learning Rust and decided to build a universal CLI for running code in many languages. The tool, Run, aims to be a single, minimal dependency utility for: running one-off snippets (from CLI flags), running files, reading and executing piped stdin, and providing language-specific REPLs that you can switch between interactively. I designed it to support both interpreted languages (Python, JS, Ruby, etc.) and compiled languages (Rust, Go, C/C++). It detects languages from flags or file extensions, can compile temporary files for compiled languages, and exposes a unified REPL experience with commands like :help, :lang, and :quit. Install: cargo install run-kit (or use the platform downloads on GitHub). Source & releases: https://ift.tt/Jw5k2yW I used Rust while following the official learning resources and used AI to speed up development, so I expect there are bugs and rough edges. I’d love feedback on: usability and UX of the REPL, edge cases for piping input to language runtimes, security considerations (sandboxing/resource limits), packaging and cross-platform distribution. Thanks — I’ll try to answer questions and share design notes.
Friday, 3 October 2025
New top story on Hacker News: LinkedIn sues software company allegedly scraping data from profiles
LinkedIn sues software company allegedly scraping data from profiles
3 by thm | 2 comments on Hacker News.
3 by thm | 2 comments on Hacker News.
Thursday, 2 October 2025
Wednesday, 1 October 2025
Tuesday, 30 September 2025
Monday, 29 September 2025
Sunday, 28 September 2025
Saturday, 27 September 2025
Friday, 26 September 2025
Thursday, 25 September 2025
Wednesday, 24 September 2025
Tuesday, 23 September 2025
Monday, 22 September 2025
Sunday, 21 September 2025
Saturday, 20 September 2025
Friday, 19 September 2025
Thursday, 18 September 2025
Wednesday, 17 September 2025
Tuesday, 16 September 2025
Monday, 15 September 2025
Sunday, 14 September 2025
Saturday, 13 September 2025
Friday, 12 September 2025
Thursday, 11 September 2025
Wednesday, 10 September 2025
New top story on Hacker News: Launch HN: Recall.ai (YC W20) – API for meeting recordings and transcripts
Launch HN: Recall.ai (YC W20) – API for meeting recordings and transcripts
18 by davidgu | 9 comments on Hacker News.
Hey HN, we're David and Amanda from Recall.ai ( https://www.recall.ai ). Today we’re launching our Desktop Recording SDK, a way to get meeting data without a bot in the meeting: https://ift.tt/jhcMG6s . It’s our biggest release in quite a while so we thought we’d finally do our Launch HN :) Here’s a demo that shows it producing a transcript from a meeting, followed by examples in code: https://www.youtube.com/watch?v=4croAGGiKTA . API docs are at https://docs.recall.ai/ . Back in W20, our first product was an API that lets you send a bot participant into a meeting. This gives developers access to audio/video streams and other data in the meeting. Today, this API powers most of the meeting recording products on the market. Recently, meeting recording through a desktop form factor instead of a bot has become popular. Many products like Notion and ChatGPT have added desktop recording functionality, and LLMs have made it easier to work with unstructured transcripts. But it’s actually hard to reliably record meetings at scale with a desktop app, and most developers who want to add recording functionality don’t want to build all this infrastructure. Doing a basic recording with just the microphone and system audio is fairly straightforward since you can just use the system APIs. But it gets a lot harder when you want to capture speaker names, produce a video recording, get real-time data, or run this in production at large scale: - Capturing speaker names involves using accessibility APIs to screen-scrape the video conference window to monitor who is speaking at what time. When video conferencing platforms change their UI, we must ship a change immediately, so this keeps working. - Producing a video recording that is clean, and doesn’t capture the video conferencing platform UI involves detecting the participant tiles, cropping them out, and compositing them together into a clean video recording. - Because the desktop recording code runs on end-user machines, we need to make it as efficient as possible. This means writing highly platform-optimized code, taking advantage of hardware encoders when available, and spending a lot of time doing profiling and performance testing. Meeting recording has zero margin for failure because if anything breaks, you lose the data forever. Reliability is especially important, which dramatically increases the amount of engineering effort required. Our Desktop Recording SDK takes care of all this and lets developers build meeting recording features into their desktop apps, so they can record both video conferences and in-person meetings without a bot. We built Recall.ai because we experienced this problem ourselves. At our first startup, we built a tool for product managers that included a meeting recording feature. 70% of our engineering time was taken up by just this feature! We ended up starting Recall.ai to solve this instead. Since then, over 2000 companies use us to power their recording features, e.g. Hubspot for sales call recording, Clickup for their AI note taker. Our users are engineering teams building commercial products for financial services, telehealth, incident management, sales, interviewing, and more. We also power internal tooling for large enterprises. Running this sort of infrastructure has led to unexpected technical challenges! For example, we had to debug a 1 in 36 million segfault in our audio encoder ( https://ift.tt/0Lqw8Pm... ), we encountered a Postgres lock-up that only occurs when you have tens of thousands of concurrent writers ( https://ift.tt/PYHxXuE ), and we saved over $1M a year on AWS by optimizing the way we shuffle data around between our processes ( https://ift.tt/A8yD35s ). You can try it here: https://www.recall.ai . It's self-serve with $5 of free credits. Pricing starts at $0.70 for every hour of recording, prorated to the second. We offer volume discounts with scale. All data recorded through Recall.ai is the property of our customers, we support 0-day retention, and we don’t train models on customer data. We would love your feedback!
18 by davidgu | 9 comments on Hacker News.
Hey HN, we're David and Amanda from Recall.ai ( https://www.recall.ai ). Today we’re launching our Desktop Recording SDK, a way to get meeting data without a bot in the meeting: https://ift.tt/jhcMG6s . It’s our biggest release in quite a while so we thought we’d finally do our Launch HN :) Here’s a demo that shows it producing a transcript from a meeting, followed by examples in code: https://www.youtube.com/watch?v=4croAGGiKTA . API docs are at https://docs.recall.ai/ . Back in W20, our first product was an API that lets you send a bot participant into a meeting. This gives developers access to audio/video streams and other data in the meeting. Today, this API powers most of the meeting recording products on the market. Recently, meeting recording through a desktop form factor instead of a bot has become popular. Many products like Notion and ChatGPT have added desktop recording functionality, and LLMs have made it easier to work with unstructured transcripts. But it’s actually hard to reliably record meetings at scale with a desktop app, and most developers who want to add recording functionality don’t want to build all this infrastructure. Doing a basic recording with just the microphone and system audio is fairly straightforward since you can just use the system APIs. But it gets a lot harder when you want to capture speaker names, produce a video recording, get real-time data, or run this in production at large scale: - Capturing speaker names involves using accessibility APIs to screen-scrape the video conference window to monitor who is speaking at what time. When video conferencing platforms change their UI, we must ship a change immediately, so this keeps working. - Producing a video recording that is clean, and doesn’t capture the video conferencing platform UI involves detecting the participant tiles, cropping them out, and compositing them together into a clean video recording. - Because the desktop recording code runs on end-user machines, we need to make it as efficient as possible. This means writing highly platform-optimized code, taking advantage of hardware encoders when available, and spending a lot of time doing profiling and performance testing. Meeting recording has zero margin for failure because if anything breaks, you lose the data forever. Reliability is especially important, which dramatically increases the amount of engineering effort required. Our Desktop Recording SDK takes care of all this and lets developers build meeting recording features into their desktop apps, so they can record both video conferences and in-person meetings without a bot. We built Recall.ai because we experienced this problem ourselves. At our first startup, we built a tool for product managers that included a meeting recording feature. 70% of our engineering time was taken up by just this feature! We ended up starting Recall.ai to solve this instead. Since then, over 2000 companies use us to power their recording features, e.g. Hubspot for sales call recording, Clickup for their AI note taker. Our users are engineering teams building commercial products for financial services, telehealth, incident management, sales, interviewing, and more. We also power internal tooling for large enterprises. Running this sort of infrastructure has led to unexpected technical challenges! For example, we had to debug a 1 in 36 million segfault in our audio encoder ( https://ift.tt/0Lqw8Pm... ), we encountered a Postgres lock-up that only occurs when you have tens of thousands of concurrent writers ( https://ift.tt/PYHxXuE ), and we saved over $1M a year on AWS by optimizing the way we shuffle data around between our processes ( https://ift.tt/A8yD35s ). You can try it here: https://www.recall.ai . It's self-serve with $5 of free credits. Pricing starts at $0.70 for every hour of recording, prorated to the second. We offer volume discounts with scale. All data recorded through Recall.ai is the property of our customers, we support 0-day retention, and we don’t train models on customer data. We would love your feedback!
Tuesday, 9 September 2025
Monday, 8 September 2025
Sunday, 7 September 2025
Saturday, 6 September 2025
New top story on Hacker News: Kenvue stock drops on report RFK Jr will link autism to Tylenol during pregnancy
Kenvue stock drops on report RFK Jr will link autism to Tylenol during pregnancy
59 by randycupertino | 180 comments on Hacker News.
59 by randycupertino | 180 comments on Hacker News.
Friday, 5 September 2025
Thursday, 4 September 2025
New top story on Hacker News: A high schooler writes about AI tools in the classroom
A high schooler writes about AI tools in the classroom
95 by dougb5 | 86 comments on Hacker News.
https://ift.tt/OzvkxGA
95 by dougb5 | 86 comments on Hacker News.
https://ift.tt/OzvkxGA
Wednesday, 3 September 2025
Tuesday, 2 September 2025
Monday, 1 September 2025
Sunday, 31 August 2025
New top story on Hacker News: Show HN: Anonymous Age Verification
Show HN: Anonymous Age Verification
7 by jwally | 4 comments on Hacker News.
So I'm not an expert in this area, but here's an attempt at cost effective, anonymous, age verification flow that probably covers ~70% of use cases in the United States. The basic premise is to leverage your bank (who already has had to perform KYC on you to open an account) to attest to your age for age-restricted merchant sites (pornhub, gambling, etc) without sharing any more information than necessary. Flow works like this: 1) You go to gambling.com 2) They request you to verify your age 3) You choose "Bank Verification" 4) You trigger a WebAuthn Credential Creation flow 5) gambling.com gives you a string to copy ------------- 6) You log into your bank 7) You go to bank.com/age-verify 8) You paste in the string you were given 9) The bank verifies it/you and creates a signed payload with your age-claims (over_18: true, over_21: false) 10) You copy this and go back to gambling.com --------------- 11) You paste the string back into gambling.com 12) You perform WebAuthn Auth flow 13) gambling.com verifies everything (signatures, webauthn, etc) 14) gambling.com sets a session-cookie and _STRONGLY_ encourages you to create an account (with a pass key). This will prevent you from having to verify your age every time you visit gambling.com The mechanics might feel off, but it feels like this in the neighborhood of a way to perform anonymous age verification. This is virtually free, and requires extremely light infra. Banks can be incentivized with small payments, or offer it because everyone else does and don't want to get left behind.
7 by jwally | 4 comments on Hacker News.
So I'm not an expert in this area, but here's an attempt at cost effective, anonymous, age verification flow that probably covers ~70% of use cases in the United States. The basic premise is to leverage your bank (who already has had to perform KYC on you to open an account) to attest to your age for age-restricted merchant sites (pornhub, gambling, etc) without sharing any more information than necessary. Flow works like this: 1) You go to gambling.com 2) They request you to verify your age 3) You choose "Bank Verification" 4) You trigger a WebAuthn Credential Creation flow 5) gambling.com gives you a string to copy ------------- 6) You log into your bank 7) You go to bank.com/age-verify 8) You paste in the string you were given 9) The bank verifies it/you and creates a signed payload with your age-claims (over_18: true, over_21: false) 10) You copy this and go back to gambling.com --------------- 11) You paste the string back into gambling.com 12) You perform WebAuthn Auth flow 13) gambling.com verifies everything (signatures, webauthn, etc) 14) gambling.com sets a session-cookie and _STRONGLY_ encourages you to create an account (with a pass key). This will prevent you from having to verify your age every time you visit gambling.com The mechanics might feel off, but it feels like this in the neighborhood of a way to perform anonymous age verification. This is virtually free, and requires extremely light infra. Banks can be incentivized with small payments, or offer it because everyone else does and don't want to get left behind.
Saturday, 30 August 2025
New top story on Hacker News: GAO warns of privacy risks in using facial recognition in rental housing
GAO warns of privacy risks in using facial recognition in rental housing
19 by Improvement | 0 comments on Hacker News.
19 by Improvement | 0 comments on Hacker News.
Friday, 29 August 2025
Thursday, 28 August 2025
Wednesday, 27 August 2025
Tuesday, 26 August 2025
Monday, 25 August 2025
Sunday, 24 August 2025
Saturday, 23 August 2025
Friday, 22 August 2025
Thursday, 21 August 2025
Wednesday, 20 August 2025
Tuesday, 19 August 2025
Monday, 18 August 2025
Sunday, 17 August 2025
New top story on Hacker News: Show HN: NextDNS Adds "Bypass Age Verification"
Show HN: NextDNS Adds "Bypass Age Verification"
28 by nextdns | 3 comments on Hacker News.
We just shipped a new feature in NextDNS: Bypass Age Verification. More and more sites (especially adult ones) are now forcing users to upload IDs or selfies to continue. We think that’s a terrible idea: handing over government documents to random sites is a huge privacy risk. This new setting workarounds those verification flows via DNS tricks. It’s available today to all users, including free accounts. We’re curious how the HN community feels about this. Is it the right way to protect privacy online, or will it just provoke regulators to push harder? https://nextdns.io
28 by nextdns | 3 comments on Hacker News.
We just shipped a new feature in NextDNS: Bypass Age Verification. More and more sites (especially adult ones) are now forcing users to upload IDs or selfies to continue. We think that’s a terrible idea: handing over government documents to random sites is a huge privacy risk. This new setting workarounds those verification flows via DNS tricks. It’s available today to all users, including free accounts. We’re curious how the HN community feels about this. Is it the right way to protect privacy online, or will it just provoke regulators to push harder? https://nextdns.io
Saturday, 16 August 2025
Friday, 15 August 2025
Thursday, 14 August 2025
Wednesday, 13 August 2025
Tuesday, 12 August 2025
Monday, 11 August 2025
Sunday, 10 August 2025
Saturday, 9 August 2025
Friday, 8 August 2025
Thursday, 7 August 2025
New top story on Hacker News: Encryption made for police and military radios may be easily cracked
Encryption made for police and military radios may be easily cracked
25 by mikece | 10 comments on Hacker News.
https://ift.tt/omgsfl9
25 by mikece | 10 comments on Hacker News.
https://ift.tt/omgsfl9
Wednesday, 6 August 2025
New top story on Hacker News: Google says AI in Search is driving more queries and higher quality clicks
Google says AI in Search is driving more queries and higher quality clicks
18 by thm | 22 comments on Hacker News.
18 by thm | 22 comments on Hacker News.
Tuesday, 5 August 2025
Monday, 4 August 2025
Sunday, 3 August 2025
Saturday, 2 August 2025
New top story on Hacker News: Introduction to Unikernel: Building, deploying lightweight, secure applications
Introduction to Unikernel: Building, deploying lightweight, secure applications
5 by eyberg | 7 comments on Hacker News.
5 by eyberg | 7 comments on Hacker News.
Friday, 1 August 2025
New top story on Hacker News: Tesla must pay $329M in damages in fatal Autopilot case, jury says
Tesla must pay $329M in damages in fatal Autopilot case, jury says
44 by koolba | 10 comments on Hacker News.
44 by koolba | 10 comments on Hacker News.
New top story on Hacker News: Show HN: TraceRoot – Open-source agentic debugging for distributed services
Show HN: TraceRoot – Open-source agentic debugging for distributed services
10 by xinweihe | 0 comments on Hacker News.
Hey Xinwei and Zecheng here, we are the authors of TraceRoot ( https://ift.tt/rvYwXth ). TraceRoot ( https://traceroot.ai ) is an open-source debugging platform that helps engineers fix production issues faster by combining structured traces, logs, source code contexts and discussions in Github PRs, issues and Slack channels, etc. with AI Agents. At the heart are our lightweight Python ( https://ift.tt/ZD5eOp6 ) and TypeScript ( https://ift.tt/1bOFG6t ) SDKs - they can hook into your app using OpenTelemetry and captures logs and traces. These are either sent to a local Jaeger ( https://ift.tt/FHaAK8C ) + SQLite backend or to our cloud backend, where we correlate them into a single view. From there, our custom agent takes over. The agent builds a heterogeneous execution tree that merges spans, logs, and GitHub context into one internal structure. This allows it to model the control and data flow of a request across services. It then uses LLMs to reason over this tree - pruning irrelevant branches, surfacing anomalous spans, and identifying likely root causes. You can ask questions like “what caused this timeout?” or “summarize the errors in these 3 spans”, and it can trace the failure back to a specific commit, summarize the chain of events, or even propose a fix via a draft PR. We also built a debugging UI that ties everything together - you explore traces visually, pick spans of interest, and get AI-assisted insights with full context: logs, timings, metadata, and surrounding code. Unlike most tools, TraceRoot stores long-term debugging history and builds structured context for each company - something we haven’t seen many others do in this space. What’s live today: - Python and TypeScript SDKs for structured logs and traces. - AI summaries, GitHub issue generation, and PR creation. - Debugging UI that ties everything together TraceRoot is MIT licensed and easy to self-host (via Docker). We support both local mode (Jaeger + SQLite) and cloud mode. Inspired by OSS projects like PostHog and Supabase - core is free, enterprise features like agent mode multi-tenant and slack integration are paid. If you find it interesting, you can see a demo video here: https://www.youtube.com/watch?v=nb-D3LM0sJM We’d love you to try TraceRoot ( https://traceroot.ai ) and share any feedback. If you're interested, our code is available here: https://ift.tt/rvYwXth . If we don’t have something, let us know and we’d be happy to build it for you. We look forward to your comments!
10 by xinweihe | 0 comments on Hacker News.
Hey Xinwei and Zecheng here, we are the authors of TraceRoot ( https://ift.tt/rvYwXth ). TraceRoot ( https://traceroot.ai ) is an open-source debugging platform that helps engineers fix production issues faster by combining structured traces, logs, source code contexts and discussions in Github PRs, issues and Slack channels, etc. with AI Agents. At the heart are our lightweight Python ( https://ift.tt/ZD5eOp6 ) and TypeScript ( https://ift.tt/1bOFG6t ) SDKs - they can hook into your app using OpenTelemetry and captures logs and traces. These are either sent to a local Jaeger ( https://ift.tt/FHaAK8C ) + SQLite backend or to our cloud backend, where we correlate them into a single view. From there, our custom agent takes over. The agent builds a heterogeneous execution tree that merges spans, logs, and GitHub context into one internal structure. This allows it to model the control and data flow of a request across services. It then uses LLMs to reason over this tree - pruning irrelevant branches, surfacing anomalous spans, and identifying likely root causes. You can ask questions like “what caused this timeout?” or “summarize the errors in these 3 spans”, and it can trace the failure back to a specific commit, summarize the chain of events, or even propose a fix via a draft PR. We also built a debugging UI that ties everything together - you explore traces visually, pick spans of interest, and get AI-assisted insights with full context: logs, timings, metadata, and surrounding code. Unlike most tools, TraceRoot stores long-term debugging history and builds structured context for each company - something we haven’t seen many others do in this space. What’s live today: - Python and TypeScript SDKs for structured logs and traces. - AI summaries, GitHub issue generation, and PR creation. - Debugging UI that ties everything together TraceRoot is MIT licensed and easy to self-host (via Docker). We support both local mode (Jaeger + SQLite) and cloud mode. Inspired by OSS projects like PostHog and Supabase - core is free, enterprise features like agent mode multi-tenant and slack integration are paid. If you find it interesting, you can see a demo video here: https://www.youtube.com/watch?v=nb-D3LM0sJM We’d love you to try TraceRoot ( https://traceroot.ai ) and share any feedback. If you're interested, our code is available here: https://ift.tt/rvYwXth . If we don’t have something, let us know and we’d be happy to build it for you. We look forward to your comments!
Thursday, 31 July 2025
New top story on Hacker News: Show HN: Sourcebot – Self-hosted Perplexity for your codebase
Show HN: Sourcebot – Self-hosted Perplexity for your codebase
15 by bshzzle | 1 comments on Hacker News.
Hi HN, We’re Brendan and Michael, the creators of Sourcebot ( https://ift.tt/LPWFqXe ), a self-hosted code understanding tool for large codebases. We originally launched on HN 9 months ago with code search ( https://ift.tt/E879F0c ), and we’re excited to share our newest feature: Ask Sourcebot. Ask Sourcebot is an agentic search tool that lets you ask complex questions about your entire codebase in natural language, and returns a structured response with inline citations back to your code. Some types of questions you might ask: - “How does authentication work in this codebase? What library is being used? What providers can a user log in with?” ( https://ift.tt/hLja1u3 ) - “When should I use channels vs. mutexes in go? Find real usages of both and include them in your answer” ( https://ift.tt/dz3ImX9 ) - “How are shards laid out in memory in the Zoekt code search engine?” ( https://ift.tt/hkUCcTx ) - "How do I call C from Rust?" ( https://ift.tt/ynqRIAU ) You can try it yourself here on our demo site ( https://ift.tt/3Ol62uz ) or checkout our demo video ( https://youtu.be/olc2lyUeB-Q ). How is this any different from existing tools like Cursor or Claude code? - Sourcebot solely focuses on code understanding . We believe that, more than ever, the main bottleneck development teams face is not writing code, it’s acquiring the necessary context to make quality changes that are cohesive within the wider codebase. This is true regardless if the author is a human or an LLM. - As opposed to being in your IDE or terminal, Sourcebot is a web app. This allows us to play to the strengths of the web: rich UX and ubiquitous access. We put a ton of work into taking the best parts of IDEs (code navigation, file explorer, syntax highlighting) and packaging them with a custom UX (rich Markdown rendering, inline citations, @ mentions) that is easily shareable between team members. - Sourcebot can maintain an up-to date index of thousands of repos hosted on GitHub, GitLab, Bitbucket, Gerrit, and other hosts. This allows you to ask questions about repositories without checking them out locally. This is especially helpful when ramping up on unfamiliar parts of the codebase or working with systems that are typically spread across multiple repositories, e.g., micro services. - You can BYOK (Bring Your Own API Key) to any supported reasoning model. We currently support 11 different model providers (like Amazon Bedrock and Google Vertex), and plan to add more. - Sourcebot is self-hosted, fair source, and free to use. Under the hood, we expose our existing regular expression search, code navigation, and file reading APIs to a LLM as tool calls. We instruct the LLM via a system prompt to gather the necessary context via these tools to sufficiently answer the users question, and then to provide a concise, structured response. This includes inline citations, which are just structured data that the LLM can embed into it’s response and can then be identified on the client and rendered appropriately. We built this on some amazing libraries like the Vercel AI SDK v5, CodeMirror, react-markdown, and Slate.js, among others. This architecture is intentionally simple. We decided not to introduce any additional techniques like vector embeddings, multi-agent graphs, etc. since we wanted to push the limits of what we could do with what we had on hand. We plan on revisiting our approach as we get user feedback on what works (and what doesn’t). We are really excited about pushing the envelope of code understanding. Give it a try: https://ift.tt/chLEkwm . Cheers!
15 by bshzzle | 1 comments on Hacker News.
Hi HN, We’re Brendan and Michael, the creators of Sourcebot ( https://ift.tt/LPWFqXe ), a self-hosted code understanding tool for large codebases. We originally launched on HN 9 months ago with code search ( https://ift.tt/E879F0c ), and we’re excited to share our newest feature: Ask Sourcebot. Ask Sourcebot is an agentic search tool that lets you ask complex questions about your entire codebase in natural language, and returns a structured response with inline citations back to your code. Some types of questions you might ask: - “How does authentication work in this codebase? What library is being used? What providers can a user log in with?” ( https://ift.tt/hLja1u3 ) - “When should I use channels vs. mutexes in go? Find real usages of both and include them in your answer” ( https://ift.tt/dz3ImX9 ) - “How are shards laid out in memory in the Zoekt code search engine?” ( https://ift.tt/hkUCcTx ) - "How do I call C from Rust?" ( https://ift.tt/ynqRIAU ) You can try it yourself here on our demo site ( https://ift.tt/3Ol62uz ) or checkout our demo video ( https://youtu.be/olc2lyUeB-Q ). How is this any different from existing tools like Cursor or Claude code? - Sourcebot solely focuses on code understanding . We believe that, more than ever, the main bottleneck development teams face is not writing code, it’s acquiring the necessary context to make quality changes that are cohesive within the wider codebase. This is true regardless if the author is a human or an LLM. - As opposed to being in your IDE or terminal, Sourcebot is a web app. This allows us to play to the strengths of the web: rich UX and ubiquitous access. We put a ton of work into taking the best parts of IDEs (code navigation, file explorer, syntax highlighting) and packaging them with a custom UX (rich Markdown rendering, inline citations, @ mentions) that is easily shareable between team members. - Sourcebot can maintain an up-to date index of thousands of repos hosted on GitHub, GitLab, Bitbucket, Gerrit, and other hosts. This allows you to ask questions about repositories without checking them out locally. This is especially helpful when ramping up on unfamiliar parts of the codebase or working with systems that are typically spread across multiple repositories, e.g., micro services. - You can BYOK (Bring Your Own API Key) to any supported reasoning model. We currently support 11 different model providers (like Amazon Bedrock and Google Vertex), and plan to add more. - Sourcebot is self-hosted, fair source, and free to use. Under the hood, we expose our existing regular expression search, code navigation, and file reading APIs to a LLM as tool calls. We instruct the LLM via a system prompt to gather the necessary context via these tools to sufficiently answer the users question, and then to provide a concise, structured response. This includes inline citations, which are just structured data that the LLM can embed into it’s response and can then be identified on the client and rendered appropriately. We built this on some amazing libraries like the Vercel AI SDK v5, CodeMirror, react-markdown, and Slate.js, among others. This architecture is intentionally simple. We decided not to introduce any additional techniques like vector embeddings, multi-agent graphs, etc. since we wanted to push the limits of what we could do with what we had on hand. We plan on revisiting our approach as we get user feedback on what works (and what doesn’t). We are really excited about pushing the envelope of code understanding. Give it a try: https://ift.tt/chLEkwm . Cheers!