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

Control what your AI can see — and what it costs. LeanCTX is an AI Value Gate for coding agents: it understands tasks, routes and compresses context, remembers what it learns, and measures cost against accepted outcomes.

Token savings are the receipt. Intelligence is the product. Works with Cursor, Claude Code, Copilot, Windsurf, Codex, Gemini and 30+ other agents — no config needed.

See it in action:

Read + Shell Map-mode reads + compressed CLI output

Gain (live) Tokens + USD savings in real time

Benchmark proof Measure compression by language + mode

_{All GIFs are generated from reproducible VHS tapes in demo/.}

Why developers use LeanCTX

• Longer useful coding sessions — less context waste = more room for actual code reasoning
• Lower API costs — reduce repeated context on reads and shell output; inspect the local savings ledger and Shadow Mode baseline for your workload
• No more "I already showed you this file" — session memory persists across chats
• Works with your existing setup — one lean-ctx setup command, no config changes needed
• Full visibility — see exactly where your context window budget goes
• Model-agnostic & yours — swap OpenAI/Anthropic/Gemini freely; your context and memory stay local and portable, never locked in a vendor's black box

Saves you tokens? Give it a star — it helps others discover LeanCTX.

Why now — own your context

Models are converging on commodity. The durable edge isn't which model you call — it's your context: what your agents read, what they remember, and what you can prove. And the layer that optimizes and owns that context can't come from the vendor that bills per token or keeps your memory in a black box — it has to sit on your side.

That's the shift behind "agent entities" that live in your chat and remember your company (Claude in Slack, ClickUp Brain): a context login, not a model login — you end up renting your own company knowledge back. LeanCTX is the opposite layer. It keeps the moat yours: local-first, portable (.ctxpkg), and model-agnostic — swap OpenAI, Anthropic or Gemini without losing context or cache. Own your context; don't rent it back.

What it does — five capabilities of an AI Value Gate

LeanCTX treats context and AI spend as managed resources, not afterthoughts. One binary covers the capabilities that decide how well an AI agent performs:

1. Context Compression — input efficiency

Your AI agent reads files and runs commands. LeanCTX compresses both automatically.

• Workload-specific token reduction on eligible context, with recovery paths and a local Shadow Mode baseline for measurement

• File reads: 10 read modes (full, map, signatures, diff, lines:N-M, density:X, …) — cached re-reads cost ~13 tokens

• Target density (density:0.4): SDE-style budget compression — keeps the highest-entropy lines until ~40% of the original tokens remain, deterministic

• JIT disclosure: signatures carries line spans and points at lines:N-M for targeted expansion — outline first, bodies on demand

• Shell output: 95+ shell-output patterns compress git, npm, cargo, docker, kubectl, terraform and more (270 passthrough rules)

• Tree-sitter AST: structural understanding for 27 languages — not just text compression

• Reversible by design (CCR): compression never discards content — pruned or truncated payloads move to a content-addressed store with a deterministic handle, so the model can pull the original bytes back on demand via ctx_expand, ctx_retrieve, an in-band marker, or GET /v1/references/{id}. Five recovery paths →

2. Intelligent Triage — task understanding

Not every task or file needs the same depth. LeanCTX classifies the task, then sends the signal rather than the noise.

• 10 read modes: from full content down to AST signatures and entropy-filtered views
• Adaptive ModePredictor: learns the optimal read mode per file type from past sessions
• IntentEngine: classifies query complexity so simple lookups stay cheap

3. Knowledge Routing — cross-source context

Relevant code, sessions, and connected sources become focused context instead of a larger prompt.

• Session memory (CCP): persist task/facts/decisions across chats — structured recovery queries survive compaction
• Knowledge graph: temporal facts with validity windows, episodic + procedural memory
• Property Graph: multi-edge code graph (imports, calls, exports, type_ref) powers impact analysis and search ranking
• Yours, not the vendor's: memory stays local and portable — export it as a .ctxpkg package and move it across machines or models, instead of locking it in a vendor's black box

4. AI Value Gate — cost and outcome tracking

Performance is the cost of a useful result, not just speed. LeanCTX records costs and outcomes locally; CPAO (Cost per Accepted Outcome) is the north-star metric for comparing useful AI work.

• Context Manager: browser dashboard with real-time token tracking, compression stats, utilization gauge
• Budgets & SLOs: profiles, roles, per-agent budgets, and throttling policies
• Context Proof (ctx_proof, ctx_verify): 4-layer verification engine with CI drift gates

5. Shadow Recommendations — savings proof

Shadow Mode compares LeanCTX treatment with a configured baseline without changing the active workflow. Its reports show cost, tokens, CPAO, and whether quality held, then recommend savings only when the comparison supports them.

Cost Intelligence

LeanCTX automatically tracks local cost and outcome signals; it does not add those reports to agent context. CPAO — cost per accepted outcome — is the north-star metric, while Shadow Mode provides a baseline comparison for savings.

lean-ctx savings --period week                 # costs, token savings, and CPAO
lean-ctx value-report --format markdown --last 20  # recent outcome quality
lean-ctx shadow --latest                       # latest baseline comparison

Quick start: value tracking

# Enable shadow mode for savings comparison
echo '[shadow]\nenabled = true' >> ~/.config/lean-ctx/config.toml

# After using LeanCTX for a while:
lean-ctx savings
lean-ctx shadow --latest

Addons — extend the engine, or run the ecosystem through one gateway

You don't have to choose between LeanCTX and the other context tools you already like. An addon is a signed package carrying either a sandboxed WASM module that runs inside the context pipeline, or an [mcp] declaration that wires an external MCP server into the gateway — after which LeanCTX treats what it returns like your own reads instead of just proxying it.

lean-ctx addon release ./my-addon   # build a signed .ctxpkg — no artifact host, no CI
lean-ctx addon add ./my-addon-1.0.0.ctxpkg   # verify, disclose, ask, install
lean-ctx addon list                 # what's installed, what loads, what's wired

• Publish it yourself — the module travels inside the signed package, so the signature covers the executable bytes. Nothing external to host, hash or serve, and no pipeline of your own.
• Verified locally, then asked — add re-checks the signature on your machine rather than trusting its source, checks every module against its pinned SHA-256, prints the publisher key and the exact command any declared server would run, and only then prompts.
• LeanCTX never installs the server for you — no uv tool install, no npx. Fetching a declared tool stays your step, where your own package manager's trust model applies. The manifest says how to run it.
• Folded in, not just proxied — opt-in post-processing runs addon output through the same pipeline as your code: compress to a budget, spill oversized blobs to a ctx_expand handle, index into BM25 / graph / knowledge. A typed integration routes specific tools straight into ctx_expand, ctx_callgraph and ctx_knowledge.
• Untrusted by default — every addon's output is scrubbed for secrets and tagged untrusted before it reaches the model. Always on, not a flag.

There is deliberately no marketplace and no addon search: LeanCTX does not host, curate or rank addons. A package is a file you install, or one you fetch from a registry you name. See the addon guide for the full walkthrough.

Where it's going

LeanCTX is growing from a single context layer into a full cognitive context layer for whole teams: version-controlled context strategy, one unified graph, and a governance layer across many agents.

• Context Time Machine → hosted history — the snapshot engine, dashboard replay, restore, and signed file-based share/import have shipped (see above); next is a ctxpkg.com registry for hosted, versioned context history and a side-by-side model-view ｜ git-diff replay. The temporal axis through everything LeanCTX does — it decides, remembers, guards, proves, and replays. (concept →)
• Context as Code — declarative pipelines, profiles, and policies in TOML, versioned like infrastructure
• Unified Context Graph — code, tests, commits, CI runs, and knowledge entries in a single semantic graph
• Agent Harness — roles, budgets, and tool permissions for multi-agent governance
• Context Observability — SLOs on context consumption, anomaly detection, OpenTelemetry / Prometheus export

The full roadmap lives in VISION.md.

How it works (30 seconds)

LeanCTX works on two planes — what your agents read and what they send to the model:

read path:   AI tool  →  (MCP tools + shell)  →  lean-ctx  →  your repo + CLI
wire path:   AI tool  →  lean-ctx proxy        →  model provider   (every request, compressed)

• MCP server (read path): exposes ctx_* tools (read modes, caching, deltas, search, memory, multi-agent)
• Shell hook (read path): transparently compresses common commands so the LLM sees less noise
• Request proxy (wire path, opt-in): lean-ctx proxy enable puts a local proxy between your agent and the model that compresses every request — system prompt, full history and tool results — prompt-cache-safe, with measured USD spend. It can also pin one reasoning-effort level across OpenAI, Anthropic & Gemini (proxy.effort) without breaking that cache, cut output tokens with a cache-safe verbosity steer plus a measured holdout, and relocate volatile fields (dates, UUIDs, commit SHAs) out of the cacheable prefix so a stable system prompt finally caches. Every rewrite is reversible (content-addressed recovery) and byte-stable by contract. Same layer as a standalone request-compression proxy (e.g. Headroom) — you don't need one on top.
• Property Graph: multi-edge code graph powers impact analysis, related file discovery, and search ranking
• Session memory: persists state with structured recovery so long-running work never "cold starts"
• Context Manager: browser dashboard for real-time visibility into what's in your context window

Get started (30 seconds)

# 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

# 2) One-command setup for your agent
lean-ctx wrap cursor      # or: wrap claude / wrap codex

# Done. Savings appear after your AI's first lean-ctx call.
lean-ctx gain

lean-ctx wrap registers the MCP server and configures the supported local transport for that agent. Undo anytime with lean-ctx unwrap cursor.

Claude Pro/Max: subscription OAuth cannot use a custom ANTHROPIC_BASE_URL. lean-ctx wrap claude therefore adds no proxy redirect while enabling the ctx_* tools and shell-output compression; an existing custom endpoint remains untouched. Claude wire-level request compression requires ANTHROPIC_API_KEY. See advanced proxy setup.

lean-ctx onboard          # connect all detected AI tools (zero prompts)
lean-ctx setup            # interactive wizard with every option

Building from source on Windows? Clone the repo and run ./install.ps1 in PowerShell — it builds the release binary and installs it into Cargo's bin directory (pass -BuildOnly to build without installing).

Real-world scenarios

LeanCTX grows with you. Below are the journeys most people actually take — each links to a complete, function-by-function walkthrough in the Reference (every CLI command and the complete MCP tools are documented there).

lean-ctx wrap cursor  # one-command setup for your agent
lean-ctx doctor       # confirm you're wired up

lean-ctx read src/server.rs -m map   # API surface, ~13 tok on re-read
lean-ctx -c "git status"             # compressed shell output

lean-ctx overview                    # task-aware project recap
lean-ctx knowledge recall "auth"     # facts that survive resets
lean-ctx knowledge consolidate       # import session + compact lifecycle
lean-ctx knowledge consolidate --all # compact every project store

lean-ctx graph impact src/auth.rs    # blast radius
lean-ctx smells scan                 # code-smell hotspots

lean-ctx provider list
lean-ctx serve --root ./api --root ./web   # multi-repo

lean-ctx doctor --fix
lean-ctx update

lean-ctx plan "refactor billing" --budget 8000
lean-ctx compile --mode balanced

ctx_agent action=register role=dev
ctx_handoff action=create        # baton-pass with full context

lean-ctx team serve --config team.toml
lean-ctx bootstrap            # zero-prompt CI setup

lean-ctx compression standard
lean-ctx harden               # enforce token discipline

lean-ctx gain --deep          # savings, cost, per-agent, heatmap
lean-ctx wrapped              # shareable recap (also: gain --svg / gain --share)
lean-ctx savings              # verified per-event ledger (auditable; savings verify)

Supported IDEs & AI tools

LeanCTX is a standard MCP server, so it works with any MCP-compatible client. Two integration modes are auto-selected per agent:

Agent compatibility matrix

Any MCP-compatible client works out of the box — the table above shows agents with first-class auto-setup.

When to use (and when not to)

Great fit if you...

• use AI coding tools daily and your sessions are shell-heavy (git/tests/builds)
• work in medium/large repos (50+ files / monorepos)
• want a local-first layer with no telemetry by default

Skip it if you...

• mostly work in tiny repos and rarely call the shell from your AI tool
• always need raw/unfiltered logs (you can still use --raw, but ROI is lower)

The honest fine print: the payoff depends on three levers — reach (own the window via the proxy/engine, not just the ctx_* tool layer), context lifetime (one long-lived session vs. a fresh process per phase), and provider pricing (prompt-cache-priced vs. re-billed every turn). They stack into a clear win where they line up and net to break-even where they don't. See the win vs. break-even matrix for the full breakdown and how to tune for each case.

Demo

Try these in any repo:

lean-ctx read rust/src/server/mod.rs -m map
lean-ctx -c "git log -n 5 --oneline"
lean-ctx gain --live
lean-ctx dashboard                              # Context Manager (browser)
lean-ctx watch                                  # TUI monitor
lean-ctx benchmark report .

• The repo ships the exact tapes used to render the GIFs in demo/
• Regenerate locally:

vhs demo/leanctx.tape
vhs demo/gain.tape
vhs demo/benchmark.tape

Benchmarks

Real, reproduced numbers — never estimated. Measured on this repo with the GPT-4o tokenizer (o200k_base); a tool that isn't installed is reported as such, never guessed.

lean-ctx's own cost is measured too: the CI-measured fixed per-session footprint (advertised tool schemas + MCP instructions + wakeup briefing) is ~3.0K tokens and gated via lean-ctx doctor overhead --gate. And the long-lived proxy rail has a deterministic self-verify — lean-ctx benchmark dual-arm --json replays a 72-turn session and prices it per model (digest f5ed145e61ce3689, 99.4% input-side saving on cache-priced rails; methodology: bench/agent-task/r2).

Accuracy isn't a vibe: the lossy stages are CI-gated. A model-free A/B gate proves the JSON crusher keeps every gold answer while cutting tokens, and proxy rewrites are byte-stable by contract, so Anthropic (90%) / OpenAI (50%) prompt-cache discounts survive compression. A deterministic off-vs-on testbench (lean-ctx eval testbench) extends the proof to answers: it runs pinned real repos through a raw-dump baseline and through lean-ctx at an identical token budget, grades free-form QA with an LLM judge and code with each repo's own tests, and emits FINDINGS.md (tokens / turns / walltime / quality) plus a regressions file — with a committed recorded subset that blocks CI on any regression.

• Latest snapshot: BENCHMARKS.md
• Reproduce: lean-ctx benchmark report .

By the numbers

• 3,000+ GitHub stars — and counting
• 280+ forks — active community contributions
• 200+ releases — shipped near-daily since launch
• 30+ supported AI coding agents — broadest MCP compatibility
• Broad MCP tool set — from simple file reads to multi-agent orchestration
• Used in production by teams running Claude Code, Cursor, and Codex daily
• Live adoption metrics: leanctx.com/metrics — installs, stars and savings, updated continuously

Docs

• Reference (every function, by user journey): docs/reference/ — 11 journeys + CLI/MCP/config appendices
• For AI agents / LLMs: llms.txt — a curated, machine-readable map of lean-ctx (per the llms.txt convention)
• Getting started: https://leanctx.com/docs/getting-started
• Tools reference: https://leanctx.com/docs/tools/
• CLI reference: https://leanctx.com/docs/cli-reference/
• What is LeanCTX: https://leanctx.com/what-is-leanctx/
• Comparison (vs RTK, Context+, MemGPT): https://leanctx.com/compare/
• Pricing & Cloud (local use is free forever): https://leanctx.com/pricing/
• FAQ: discord-faq.md
• Feature catalog (SSOT snapshot): LEANCTX_FEATURE_CATALOG.md
• Monorepo guide: docs/guides/monorepo.md
• Architecture: ARCHITECTURE.md
• Vision: VISION.md

Privacy & security

• No telemetry by default
• Optional anonymous stats sharing (opt-in during setup)
• Disableable update check (config update_check_disabled = true or LEAN_CTX_NO_UPDATE_CHECK=1)
• 40+ security hardening fixes in v3.5.16 (path traversal, injection, CSPRNG, CSP, resource limits — details)
• Context Governance Benchmark self-assessment: graded C2 — Managed against the 32-control CGB v1.0-draft spec, gaps declared — docs/compliance/cgb-self-assessment.md
• Runs locally; your code never leaves your machine unless you explicitly enable cloud sync

See SECURITY.md.

Uninstall

One command removes everything — it stops all processes, then deletes hooks, editor configs, rules, autostart (LaunchAgent/systemd), the data dir, and the binary itself:

lean-ctx uninstall                 # full clean removal
lean-ctx uninstall --dry-run       # preview every change, write nothing
lean-ctx uninstall --keep-config   # keep MCP configs + rules (for reinstall)
lean-ctx-off                       # or just disable for the current shell session

No binary on PATH (or you used the curl installer)? Run the same removal from the installer:

curl -fsSL https://leanctx.com/install.sh | sh -s -- --uninstall

If you installed via a package manager, uninstall removes everything it wrote and tells you the one command to finish removing the binary:

brew uninstall lean-ctx        # Homebrew
cargo uninstall lean-ctx       # cargo install
npm uninstall -g lean-ctx-bin  # npm

Star History

Contributing

Start with CONTRIBUTING.md. Easy first PR: propose a new CLI compression pattern via the issue template.

License

Apache License 2.0 — see LICENSE.