Lightweight Knowledge Graph for AI-Assisted Development
LeanKG is a local-first knowledge graph that gives AI coding tools accurate codebase context. It indexes your code, builds dependency graphs, and exposes an MCP server so tools like Cursor, OpenCode, and Claude Code can query the knowledge graph directly. No cloud services, no external databases.
Visualize your knowledge graph with force-directed layout, WebGL rendering, and community clustering.
See docs/web-ui.md for more features.
Try LeanKG without installing: https://leankg.onrender.com
leankg web --port 9000curl -fsSL https://raw.githubusercontent.com/FreePeak/LeanKG/main/scripts/install.sh | bash -s -- <target>Supported targets:
| Target | AI Tool | Auto-Installed |
|---|---|---|
opencode |
OpenCode AI | Binary + MCP + Plugin + Skill + AGENTS.md |
cursor |
Cursor AI | Binary + MCP + Skill + AGENTS.md + Session Hook |
claude |
Claude Code | Binary + MCP + Plugin + Skill + CLAUDE.md + Session Hook |
gemini |
Gemini CLI | Binary + MCP + Skill + GEMINI.md |
kilo |
Kilo Code | Binary + MCP + Skill + AGENTS.md |
antigravity |
Google Antigravity | Binary + MCP + Skill + GEMINI.md |
Examples:
curl -fsSL https://raw.githubusercontent.com/FreePeak/LeanKG/main/scripts/install.sh | bash -s -- cursor
curl -fsSL https://raw.githubusercontent.com/FreePeak/LeanKG/main/scripts/install.sh | bash -s -- claudecargo install leankg && leankg --versiongit clone https://github.com/FreePeak/LeanKG.git && cd LeanKG && cargo build --releaseleankg init # Initialize LeanKG in your project
leankg index ./src # Index your codebase
leankg watch ./src # Auto-index on file changes
leankg impact src/main.rs --depth 3 # Calculate blast radius
leankg status # Check index status
leankg metrics # View token savings
leankg web # Start Web UI at http://localhost:8080
# Obsidian vault sync
leankg obsidian init # Initialize Obsidian vault structure
leankg obsidian push # Push LeanKG data to Obsidian notes
leankg obsidian pull # Pull annotation edits from Obsidian
leankg obsidian watch # Watch vault for changes and auto-pull
leankg obsidian status # Show vault status
# Microservice call graph (via Web UI)
leankg web # Start Web UI at http://localhost:8080
# Then visit http://localhost:8080/servicesSee docs/cli-reference.md for all commands.
LeanKG auto-triggers in Claude Code sessions via PreToolUse hooks that route search intents to LeanKG tools instead of native tools.
# Install LeanKG with Claude Code hooks and plugin
leankg setup
# Then restart Claude Code or run:
/reload-pluginsWhat leankg setup installs:
.claude-plugin/- Plugin manifest for Claude Code validationhooks/- PreToolUse, SessionStart, PostToolUse hooks- Adds
leankg@localtoenabledPluginsin~/.claude/settings.json
Auto-trigger behavior:
SessionStarthook injects tool selection hierarchy into every sessionPreToolUsehook nudges toward LeanKG when you use Grep/Read/Bash for code analysis- LeanKG returns token-optimized context instead of scanning entire files
graph LR
subgraph "Without LeanKG"
A1[AI Tool] -->|Full codebase context| B1[15,000-45,000 tokens]
B1 --> A1
end
subgraph "With LeanKG"
A2[AI Tool] -->|Targeted subgraph| C[LeanKG Graph]
C -->|Context reduction| A2
end
Without LeanKG: AI processes full context from files found via grep/search. With LeanKG: AI queries knowledge graph for targeted context. Token reduction varies by task complexity (see benchmark results).
- Auto-Init -- Install script configures MCP, rules, skills, and hooks automatically
- Auto-Trigger -- Session hooks inject LeanKG context into every AI tool session
- Token Optimized -- Targeted subgraph retrieval vs full file scanning
- Impact Radius -- Compute blast radius before making changes
- Dependency Graph -- Build call graphs with
IMPORTS,CALLS,TESTED_BYedges - MCP Server -- Expose graph via MCP protocol for AI tool integration
- Multi-Language -- Index Go, TypeScript, Python, Rust, Java, Kotlin with tree-sitter
- Android -- Extract XML layouts, resources, and manifest relationships
See docs/architecture.md for system design and data model details.
| Tool | Auto-Setup | Session Hook | Plugin |
|---|---|---|---|
| Cursor | Yes | session-start | - |
| Claude Code | Yes | session-start | Yes |
| OpenCode | Yes | - | Yes |
| Kilo Code | Yes | - | - |
| Gemini CLI | Yes | - | - |
| Google Antigravity | Yes | - | - |
| Codex | Yes | - | - |
Note: Cursor requires per-project installation. The AI features work on a per-workspace basis, so LeanKG should be installed in each project directory where you want AI context injection.
See docs/agentic-instructions.md for detailed setup and auto-trigger behavior.
Track token savings to understand LeanKG's efficiency.
leankg metrics --json # View with JSON output
leankg metrics --since 7d # Filter by time
leankg metrics --tool search_code # Filter by toolSee docs/metrics.md for schema and examples.
# Check current version
leankg version
# Update LeanKG binary (kills processes, removes old binary, installs hooks)
leankg update
# Or via install script
curl -fsSL https://raw.githubusercontent.com/FreePeak/LeanKG/main/scripts/install.sh | bash -s -- update
# Obsidian vault sync
leankg obsidian init # Initialize Obsidian vault
leankg obsidian push # Push LeanKG data to Obsidian notes
leankg obsidian pull # Pull annotation edits from Obsidian| Doc | Description |
|---|---|
| docs/cli-reference.md | All CLI commands |
| docs/mcp-tools.md | MCP tools reference |
| docs/agentic-instructions.md | AI tool setup & auto-trigger |
| docs/architecture.md | System design, data model |
| docs/web-ui.md | Web UI features |
| docs/metrics.md | Metrics schema & examples |
| docs/benchmark.md | Performance benchmarks |
| docs/roadmap.md | Feature planning |
| docs/tech-stack.md | Tech stack & structure |
| docs/android-extraction.md | Android XML & resource extraction |
If you see database is locked (code 5), another LeanKG process is holding the database:
# Kill all leankg and vite processes
leankg-kill
# Or manually
pkill -9 -f "leankg"
pkill -9 -f "vite"leankg proc kill # Kill all leankg and vite processes
leankg proc status # Show running leankg/vite processesImportant: Always kill the web server before indexing to avoid database lock conflicts.
| Operation | Throughput |
|---|---|
| Insert elements | ~57,618 elements/sec |
| Insert relationships | ~67,067 relationships/sec |
| Retrieve all elements | ~418,718 elements/sec |
| Cache speedup (cold to warm) | 345-461x |
Run load tests:
cargo test --release load_test -- --nocaptureSee tests/benchmark/results/clean-benchmark-2026-04-21.md for detailed A/B testing results comparing LeanKG vs baseline code search.
- Rust 1.70+
- macOS or Linux
MIT