lean-ctx is a MCP and tool-calling integration repository at yvgude/lean-ctx; the project summary says: 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 recorded primary language is Rust. License metadata lists Apache-2.0. GitHub metadata shows about 2,345 stars. The project homepage is https://leanctx.com.
License
Apache-2.0
Stars
3,076
Homepage
https://leanctx.com/Features
- GitHub description for lean-ctx: 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.
- lean-ctx uses Rust as its recorded primary language, which helps with stack-fit review.
- lean-ctx shows how external tools or MCP-style capabilities may connect around the project.
- lean-ctx fits engineering teams assessing code, CLI, SDK, runtime, or developer-tooling workflows.
- lean-ctx lists Apache-2.0 license metadata; review obligations before redistribution or hosted use.
- lean-ctx has about 2,345 GitHub stars in the local metadata snapshot.
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
Start from the 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.), then verify maintenance status, integration boundaries, and whether its MCP and tool-calling integration, developer engineering workflows focus matches the intended workflow. Repository: https://github.com/yvgude/lean-ctx. Stars: about 2,345. License: Apache-2.0. Language: Rust.
lean-ctx is best treated as a repository-level component or reference implementation for MCP and tool-calling integration, developer engineering workflows. Good evaluation scenarios include: Test lean-ctx when the need is MCP and tool-calling integration and the repo summary matches: LeanCTX — the Context OS for AI development. One local binary that compresses, remember... Compare the Rust implementation in lean-ctx before choosing a similar internal architecture. Use lean-ctx to connect tool-enabled agent workflows to the repository capability.
