| name | lean-ctx |
| description | Context Runtime for AI Agents — 67 MCP tools, 10 read modes, 60+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present. |
LeanCTX — Context Runtime for AI Agents
LeanCTX optimizes LLM context through 67 MCP tools, 60+ shell compression patterns, and tree-sitter AST parsing for 18 languages. It provides adaptive file reading, cross-session memory (CCP), task-conditioned relevance scoring, and a feedback loop for learning optimal compression.
Setup (run first)
Before using lean-ctx, verify it is installed:
which lean-ctx || bash scripts/install.sh
If the install script is not available locally, install manually:
curl -fsSL https://raw.githubusercontent.com/yvgude/lean-ctx/main/skills/lean-ctx/scripts/install.sh | bash
After installation, run the one-command setup (installs shell hook + editor wiring + rules + skills):
lean-ctx setup
lean-ctx supports two integration styles:
- CLI-redirect (preferred when shell access exists): no MCP tool schema overhead.
- MCP (required for some IDE extensions): cached reads + tools via MCP.
When to use lean-ctx
Always prefer lean-ctx -c <command> over running commands directly when:
- The command produces verbose output (build logs, git diffs, dependency trees, test results)
- You are reading files and only need the structure or API surface
- You want to check token savings for the current session
Shell commands (use instead of raw exec)
lean-ctx -c git status
lean-ctx -c git diff
lean-ctx -c git log --oneline -10
lean-ctx -c npm install
lean-ctx -c cargo build
lean-ctx -c cargo test
lean-ctx -c docker ps
lean-ctx -c kubectl get pods
lean-ctx -c aws ec2 describe-instances
lean-ctx -c helm list
lean-ctx -c prisma migrate dev
lean-ctx -c curl -s <url>
lean-ctx -c ls -la <dir>
Supported: git, npm, pnpm, yarn, bun, deno, cargo, docker, kubectl, helm, gh, pip, ruff, go, eslint, prettier, tsc, aws, psql, mysql, prisma, swift, zig, cmake, ansible, composer, mix, bazel, systemd, terraform, make, maven, dotnet, flutter, poetry, rubocop, playwright, curl, wget, and more.
File reading (compressed modes)
lean-ctx read <file>
lean-ctx read <file> -m map
lean-ctx read <file> -m signatures
lean-ctx read <file> -m aggressive
lean-ctx read <file> -m entropy
lean-ctx read <file> -m diff
Use map mode when you need to understand what a file does without reading every line.
Use signatures mode when you need the API surface of a module (tree-sitter for 18 languages).
Use full mode only when you will edit the file.
AI Tool Integration
lean-ctx init --global
lean-ctx init --agent cursor --mode cli-redirect
lean-ctx init --agent claude --mode cli-redirect
lean-ctx init --agent codex --mode cli-redirect
lean-ctx init --agent opencode --mode cli-redirect
lean-ctx init --agent copilot
lean-ctx init --agent jetbrains
lean-ctx init --agent windsurf
Multi-Agent & Knowledge
CLI (works in CLI-redirect and MCP setups):
lean-ctx knowledge remember "value" --category <c> --key <k>
lean-ctx knowledge recall "query"
lean-ctx knowledge search "query"
lean-ctx knowledge export [--format json|jsonl|simple] [--output <path>]
lean-ctx knowledge import <path> [--merge replace|append|skip-existing] [--dry-run]
lean-ctx knowledge remove --category <c> --key <k>
lean-ctx session task "what you're doing"
lean-ctx session finding "what you found"
lean-ctx session decision "what you decided"
lean-ctx session save
If MCP is enabled for your IDE, the same capabilities are also available as MCP tools
(ctx_knowledge, ctx_session, ctx_agent, ...).
Additional Intelligence Tools
ctx_edit(path, old_string, new_string) — search-and-replace file editing without native Read/Editctx_overview(task) — task-relevant project map at session startctx_preload(task) — proactive context loader, caches task-relevant filesctx_semantic_search(query) — BM25 code search by meaning across the projectctx_intent now supports multi-intent detection and complexity classification- Semantic cache: TF-IDF + cosine similarity for finding similar files across reads
Session Continuity (CCP)
lean-ctx sessions list
lean-ctx sessions show
lean-ctx wrapped
lean-ctx wrapped --month
lean-ctx benchmark run
lean-ctx benchmark run --json
lean-ctx benchmark report
MCP tools for CCP:
ctx_session status — show current session state (~400 tokens)ctx_session load — restore previous session (cross-chat memory)ctx_session task "description" — set current taskctx_session finding "file:line — summary" — record key findingctx_session decision "summary" — record architectural decisionctx_session save — force persist session to diskctx_gain action=wrapped — generate savings report card in chatctx_refactor — LSP-powered rename, references, definition, implementations (requires language server)ctx_expand action=search_all query="..." — FTS5 cross-archive fulltext search
Analytics
lean-ctx gain
lean-ctx dashboard
lean-ctx session
lean-ctx discover
Tips
- The output suffix
[lean-ctx: 5029→197 tok, -96%] shows original vs compressed token count
- For large outputs, lean-ctx automatically truncates while preserving relevant context
- JSON responses from curl/wget are reduced to schema outlines
- Build errors are grouped by type with counts
- Test results show only failures with summary counts
- Cached re-reads cost only ~13 tokens
