Meet Contextual
A local-first temporal context engine for your AI agents
What it does
Contextual is a local-first CLI/MCP daemon that gives any AI coding agent (Claude Code, Cursor, Copilot, and more) a persistent, structurally accurate memory of your codebase built from a real dependency graph and AST parsing, not text similarity or guesswork. 0 bytes of your code ever leave your machine. 5 mins to contextualise on 50k LOC, 94.5 ms median recall latency, so your AI tools finally know your code as well as you do.
A local-first AI context engine with semantic search, temporal recall, and on-device indexing.
Temporal semantic search that remembers everything your AI forgets. A context engine that runs entirely on your machine — indexed, queryable, and aware of how your repository changed over time. Contextual is engineered around the smallest set of ideas that make a codebase searchable through time, on a single laptop, without sending anything out. Ask in plain English. Get back the exact function, commit, decision, or doc paragraph that matters — ranked by meaning, not keywords. Every symbol, comment and PR is anchored in time. Ask "what did this file mean last quarter?" and walk the answer backwards. Every function, commit, and doc is a node — calls, imports, and edits are edges. Trace…from contextuallabs.dev
Does the same job
all alternatives →
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 · 17d 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 · 17d ago · simedw.com