DevRecall
On-device memory for everything you ship
What it does
Most tools that remember your work ship it to someone's cloud. DevRecall keeps a searchable index of your whole work history on your laptop — local SQLite, offline embeddings, nothing leaves the machine. It pulls from Git, GitHub, Slack, Jira, Linear and Confluence, then links each ticket to the commits, PRs and threads that resolved it. Ask "what was that auth bug in February?" and answers cite real rows. Also an MCP server, so Claude Code and Cursor recall your history inline. MIT.
On-device developer memory. Chat your work history, generate standups, and write brag docs from Git, Slack, Calendar, Jira, and Linear — all data stays on your machine.
DevRecall is on-device memory for engineers. Chat your work history, generate standups, and write brag docs from Git, Slack, Calendar, Jira, Linear, Confluence, Notion, and your Claude Code sessions — without your activity ever leaving this laptop. Ships an MCP server, so your AI coding tool finally remembers what you've shipped. DevRecall keeps an on-device, embedding-searchable index of your work. Ask it questions, or let it write the routine docs for you. An agent with read-only tools over your local index — FTS5 keyword search, vector search, date and source filters. Ask "what was that auth bug I fixed in February?" and it filters by date, then semantic-matches. Every answer cites the…from devrecall.dev
Does the same job
all alternatives →
- DADevUtils.app – Developer Utilities for macOS2020 · ▲241
This is a project I've been working on since the start of Covid-19. I built an app so that I don't have to put data into online tools like JWT debugger, JSON formatter, URL decoder, etc... https://devutils.app The app works entirely offline and is open-source. I'm selling the pre-built version of the app to earn some revenue for my time. If you want to try the app but can't afford the price or don't have XCode to build the app, drop me an email (my profile), I'll be happy to provide you a free build. I would love to hear all the feedback/suggestions. Thanks!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com