lean-ctx (yvgude/lean-ctx) is an open-source AI project on GitHub. Repository summary: LeanCTX — the Context OS for AI development. One local binary that compresses, remembers, routes, and verifies every token between your code and the model. 63 MCP tools, 10 read modes, up to 99% token savings. Works with Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini. Its focus includes MCP and tool-calling integration, developer-centric engineering workflows. It is suitable for extension, integration, and iterative delivery in real workflows.
License
Apache-2.0
Stars
2,345
Homepage
https://leanctx.com/Features
- Core capability: LeanCTX — the Context OS for AI development. One local binary that compresses, remembers, routes, and verifies every token between your code and the model. 63 MCP tools, 10 read modes, up to 99% token savings. Works with Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini.
- Provides MCP or tool-calling integration
- Built for code generation, debugging, or engineering integration
- Repository: yvgude/lean-ctx
- Primary language: Rust
- Open-source license: Apache-2.0
Use Cases
- Connects external systems into agent workflows
- Supports AI engineering build-and-iterate workflows for dev teams
- Build internal AI workflow prototypes with lean-ctx
- Validate lean-ctx in production-like engineering scenarios
- Building AI development workflows
- Automating agent-based processes
FAQ
Teams should first define integration boundaries and call patterns, then map repository capabilities into concrete interfaces, parameters, and access rules. GitHub repository: https://github.com/yvgude/lean-ctx. Community traction is around 2,345 stars. License: Apache-2.0.
It usually works as an execution component or capability layer, with common deployment fits such as: Connects external systems into agent workflows, Supports AI engineering build-and-iterate workflows for dev teams, Build internal AI workflow prototypes with lean-ctx.
