whereismyai
Graft
Graft is an open-source context layer that maps codebases into plain-English pages to orient coding agents.
Graft is an open-source context layer designed for large codebases. It maps repositories into a graph of linked, plain-English pages committed directly to git. This allows coding agents like Claude Code, Cursor, and Codex to start sessions oriented rather than searching from cold. The tool uses Tree-sitter parsing to create deterministic abstract syntax trees across over twenty languages without requiring an API key. It operates locally via an MCP server or CLI using files committed to your repo, requiring no separate server, database, or embeddings. A separate model grades every answer to ensure correctness while providing impact analysis to show a symbol's blast radius before making changes.
Graft at a glance
- Best for: Software engineer
- Runs on: CLI, self-hosted, open source
- Pricing: Free
- Released: July 2026
- Category: AI coding tool
- Website: trailhq.com
Key features
- Maps repositories into plain-English pages committed to git
- Tree-sitter parsing for deterministic ASTs across 20+ languages
- MCP server and CLI integration for coding agents
- Impact analysis showing blast radius before editing
- Background map rebuilding during edits
- Independent model grading for answer correctness
Use it for
- Orienting coding agents before they edit large codebases
- Analyzing the blast radius of code symbols before changes
- Reducing token usage and tool calls for AI coding assistants
Companions
Tools that articles about Graft recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to Graft
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
- pstack — Improves AI coding agent outcomes with rigorous workflows.
- ModLens — Converts screenshots and charts into structured JSON data for coding agents.
- Claude Context — It reduces token costs and provides deep context for large codebases.
- SuperClaude — Adds 30 slash commands and 8 MCP servers to Claude Code.
- CodeSight — Reduces AI token usage significantly and maps projects instantly.
- Axiomcodegraph — Resolves calls from types rather than syntax for higher accuracy.
- Context Engineering Kit — Improves agent reliability and code generation quality with minimal token footprint.
- Enzyme — It indexes markdown notes locally so AI coding agents can cite them.
- Tstack — Automates complex pull request workflows and multi-model code reviews.
All Graft alternatives