Claudius

lean-ctx

MCP

MCP server providing context compression, memory routing, and token optimization with 63 tools for AI coding assistants.

by yvgude·yvgude/lean-ctx·Rust·v3.7.5
50· C
Install
git clone https://github.com/yvgude/lean-ctx
Stars
2,536
7d change
Downloads / week
Last active
today
About

██╗ ███████╗ █████╗ ███╗ ██╗ ██████╗████████╗██╗ ██╗ ██║ ██╔════╝██╔══██╗████╗ ██║ ██╔════╝╚══██╔══╝╚██╗██╔╝ ██║ █████╗ ███████║██╔██╗ ██║ ██║ ██║ ╚███╔╝ ██║ ██╔══╝ ██╔══██║██║╚██╗██║ ██║ ██║ ██╔██╗ ███████╗███████╗██║ ██║██║ ╚████║ ╚██████╗ ██║ ██╔╝ ██╗ ╚══════╝╚══════╝╚═╝ ╚═╝╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝ ╚═╝

The Cognitive Context Layer for AI coding agents

Your AI coding agent wastes thousands of tokens rereading files, parsing noisy shell output, and losing context between sessions — and you have no control over any of it.

LeanCTX is the operating system for that context. One local binary that governs every token between your code and the model: it compresses what the AI reads, remembers what matters across sessions, routes each read to the right fidelity, and verifies what comes back. Zero config required. Local-first.

Read more on GitHub →
30-day stars
collecting…
Trust factors
Source
community
Known advisories
0
Maintenance
active
License
none
Age
0 months
token-efficiencydeveloper-toolsmemory#context-engineering#token-optimization#rust#claude-code#cursor#agentic-coding#ai#ai-coding#context-layer#copilot#gemini-cli#llm#mcp#reduce-token-costs