recon
35× fewer tokens for AI coding agents
What it does
Local-first MCP server for AI coding agents. A 24 MB Rust binary that replaces Read, Grep, and Glob with 12 symbol-aware tools — 15–35× token reduction, 8 ms queries on 320K symbols. Your code never leaves your machine.
Does the same job
all alternatives →
Remote OpenClawJul 2026 · codexmarketplaces.com · ▲8113,000+ MCP servers, skills & plugins for AI coding agents
- HMht-mcp – a Rust MCP server of headless terminal for agents2025 · github.com · ▲25
We built a Rust MCP server, which wraps the excellent headless terminal (HT)[1] to makes it available for agentic coding tools. Most agentic coding tools struggle with blocking, interactive terminal tools (all the boilerplate generator, infra CLI tools etc). This is because many existing CLI dev tools are built for humans and require interactive input. We built this so agentic coding tools (Claude Code, Cursor, Memex, etc) can “see” and “interact” with terminals exactly like humans do. In our demo video [2], you'll see it operating vim/emacs just as a human would - selecting options,…
- MCMicroCodex Coding Agent – OpenAI/codex reimplemented in C++ <1MB binaryAug 2026 · github.com · ▲19
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 · 27d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app