workflowstacks
mcp-server

lean-ctx cuts token usage and secures AI context for founders

Lean-CTX is a local Rust binary that trims token costs by up to 90% while controlling and auditing what AI agents read and store—ideal for founders building safe, efficient AI products. 3.9k+ GitHub stars.

From the repo · “LeanCTX — Context Gateway for AI Systems. Control what your AI can see. Open-source Engine for context selection, supported controls, and evidence.”

3,898 stars+21★ this week355 forksRustGuide quality 8/10 · reviewed Oct 19Updated 10/22/2026100% free · open source
What it does

LeanCTX is a context intelligence layer that controls what AI agents can see, remember, and save, optimizing token usage by 60-90%.

When to use it
  • •When integrating multiple AI agents into a startup's workflow
  • •When sensitive data needs to be protected from unauthorized AI access
  • •When optimizing token usage is crucial for cost reduction
Ready-to-paste prompt
Run `./target/release/lean-ctx --config lean-ctx.conf --agent my_agent` to start the LeanCTX server with a custom configuration for a specific AI agent
Heads up: Ensure the `RUST_LOG` environment variable is set to the desired log level (e.g., `RUST_LOG=info`) to avoid silent failures or unexpected behavior
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/lean-ctx && curl -fsSL https://workflowstacks.com/api/skills/lean-ctx/claude-skill -o ~/.claude/skills/lean-ctx/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How lean-ctx cuts token usage and secures AI context for founders works
Codeflow
Free to inspect

Lean-ctx cuts token usage and secures AI context for founders is a very large Rust project (~677k lines across 2352 code files, plus 276 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~677k lines · 2352 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 3 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Nothing to install on your machine
Rust 87%C 4%Python 3%JavaScript 3%TypeScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    bin/lctx
    Where the program starts running
  4. 4
    skills/lean-ctx-review/SKILL.md
    Inside skills/ — an example of what the AI is told to do
  5. 5
    cookbook/.biomeignore
    A worked example — copy this to get going
What's in each folder
skills/Prompts, skills & agent definitions4 files
packages/Sub-packages / plugins61 files
integrations/Sub-packages / plugins34 files
bin/Command-line entry points1 files
docs/Documentation295 files
cookbook/Examples you can copy47 files
examples/Examples you can copy18 files
rust/Folder2446 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
yvgude
Language
Rust
Category
mcp-server
Published
3/23/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/lean-ctx.svg)](https://workflowstacks.com/skills/lean-ctx?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

MCP config

Filesystem MCP config

Let Claude read and write files in folders you choose.

MCP config

Puppeteer (browser) MCP config

Let Claude control a headless browser — navigate, screenshot, scrape.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 355,695
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,361
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 131,266
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 2,642
pinvou-agent: Boost productivity with a desktop AI assistant
pinvou-agent lets founders automate tools, manage files, and run workflows locally, turning knowledge into real deliverables. 2.6k+ GitHub stars.
mcp-server★ 7,296
unstract: Turn messy docs into structured JSON with LLM power
Extract data from PDFs, scans, and any unstructured source via API or ETL pipelines. Ideal for founders building AI‑driven data pipelines. 7.3k+ GitHub stars
mcp-server★ 6,217
claude-code-ultimate-guide – Master Claude‑powered coding workflows
A founder’s reference for building agentic Claude Code apps with ready‑made hooks, MCP servers, quizzes, and production templates. Ideal for Python teams seeking AI‑pair programming best practices. 6.1k+ GitHub stars.