Stars
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
The agent that grows with you
Desktop app to manage markdown knowledge bases
Useful resources on distributed system design.
A commenting system powered by GitHub Discussions. 💬 💎
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Production-grade engineering skills for AI coding agents.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Codemogger is a code indexing library and MCP server for AI coding agents
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Build smaller, faster, and more secure desktop and mobile applications with a web frontend.
Lightweight agent orchestration dev tool that lives in your repo
aider is AI pair programming in your terminal
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
The official Rust SDK for the Model Context Protocol
Code to accompany Refactoring to Rust
A SQL database in Rust: SQLite-compatible, now also speaking Postgres (experimental). The LLVM of databases.
Bookmarks Extension for Visual Studio Code
Copilot Chat extension for VS Code
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.