Your AI deserves
better context.

Five things LeanCTX does to every token.

Between your AI and your code, one local binary runs the same five-step loop on every read, command, and search: perceive, compress, remember, route, and govern — so your AI sees the signal, keeps it, and stays in bounds.

Beyond the IDE: embed LeanCTX in your own agent via lean-ctx serve and the versioned /v1 API with Python, TypeScript and Rust SDKs, reshape it for any domain with Context Personas, index PDFs, HTML and CSV locally, and extend it with plugins and WASM — every local feature stays free.

Start where you are.

Twenty-eight code-grounded journeys, grouped into four tracks. Pick the one that sounds like you and follow it end to end — from your first install to running LeanCTX across a whole team.

Every kind of context, the right way.

LeanCTX applies a different strategy to each kind of context — so the model sees the signal, and you stay in control of the rest.

Nothing is lost. Compression is reversible — the full content is one ctx_retrieve away, and LeanCTX tells your AI exactly when to ask for it.

You already have tools. Here's the difference.

LeanCTX isn't a replacement for grep or your editor — it's the layer that decides what's worth your AI's attention.

See compression in action.

Real TypeScript code. Real LeanCTX output. Pick a mode and watch the transformation.

import { verify, sign } from 'jsonwebtoken';
import { Redis } from 'ioredis';

const redis = new Redis(process.env.REDIS_URL);
const JWT_SECRET = process.env.JWT_SECRET!;

export async function authenticate(token: string) {
  const payload = verify(token, JWT_SECRET);
  const session = await redis.get(`session:${payload.sub}`);
  if (!session) throw new Error('Session expired');
  return JSON.parse(session);
}

export function refreshSession(userId: string) {
  return sign({ sub: userId }, JWT_SECRET, { expiresIn: '1h' });
}

exports: authenticate(token), refreshSession(userId)
deps: jsonwebtoken, ioredis
types: string → Promise<object>, string → string
lines: 17  size: 4,200 → 180 tokens
cached: 13 tokens on re-read

fn authenticate(token: string): Promise<object>
fn refreshSession(userId: string): string

4,200 → 95 tokens
cached: 13 tokens

exports: authenticate(token), refreshSession(userId)
deps: jsonwebtoken (verify, sign), ioredis (Redis)
pattern: JWT auth + Redis sessions
4,200 → 150 tokens
cached: 13 tokens

Same model. Fraction of the tokens.

Works with every AI coding tool.

One install. Zero config per tool. LeanCTX auto-detects and integrates with all major AI coding tools.