GraphCanon updated 2w · GitHub synced 2w
Decision brief
LeanCTX serves as a context intelligence layer for AI agents, providing localized control over read access and memory management while optimizing token usage for numerous MCP tools, all powered by a local Rust binary.
Good fit when
- When you require granular, localized oversight over what your AI can visualize, learn from, and store within its operations.
- If your project involves more than 70 MCP tools or uses multiple programming languages and needs token optimization to keep costs down.
Avoid when
- When there is a dependence on cloud-based solutions for context intelligence, since LeanCTX operates as a local binary.
- If your setup does not need context layering or token optimization. In such cases, using LeanCTX would incur overhead without providing significant benefits.
Observed Jul 14, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 2w
- Provenance
- Not a fork · Personal account
- As of 2w
- Security (OSV)
- No MCP manifest
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
cargo add lean-ctxSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
LeanCTX acts as a context intelligence layer for AI agents, controlling read access and memory management locally. It supports token optimization for more than 70 MCP tools with support for multiple programming languages.
Capability facts
- Languages
- rust
Source: github.language · Aug 4, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 4, 2026)
Framework adapters included (LiteLLM, LangChain, Vercel AI SDK). → **[compress() cookbook](docs/guides/compress-sdk.md)**Source link
Source: README excerpt (regex_v1, Aug 4, 2026)
npm install -g lean-ctx-bin # Node.jsSource link
Source: README excerpt (regex_v1, Aug 4, 2026)
pip install lean-ctx-client # Python (imports as `leanctx`)Source link
Tags
README
1) Install (pick one)
curl -fsSL https://leanctx.com/install.sh | sh # universal (no Rust needed) brew tap yvgude/lean-ctx && brew install lean-ctx # macOS / Linux npm install -g lean-ctx-bin # Node.js cargo install lean-ctx # Rust pi install npm:pi-lean-ctx # Pi Coding Agent
pip install lean-ctx-sdk
from lean_ctx import compress messages = compress(messages, model="claude-sonnet-4")
```ts
// npm install lean-ctx-sdk
import { compress } from "lean-ctx-sdk";
messages = await compress(messages, { model: "gpt-4o" });
Framework adapters included (LiteLLM, LangChain, Vercel AI SDK). → compress() cookbook
Thin /v1 contract clients — lean-ctx-client (npm · crates.io). Wrap the full /v1 tool, event and session API over the process boundary — never links the engine, so it stays stable as lean-ctx evolves.
pip install lean-ctx-client # Python (imports as `leanctx`)
npm install lean-ctx-client # TypeScript / Node
cargo add lean-ctx-client # Rust
Start the server with lean-ctx serve, then point a client at it. → API reference
License
Apache License 2.0 — see LICENSE.
--- lean-ctx: ctx_compose bundles search+read+symbols in one call ---
For agents
This page has a .md twin and JSON over the API.