trailhq/Graft
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Earlier source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Stop repeating yourself to your coding agent. You correct it, and by the next session it has forgotten. Trail manages your CLAUDE.md and AGENTS.md so it doesn't. • Every correction you make becomes a rule your agent keeps. • The ones that can't break get a hook that blocks it, not a note it ignores. That is the whole setup. graft init asks which of your coding agents to wire up, builds graft/ from your code, and drops a statusline and hooks into .claude/, so from the next session on Graft rides along in Claude Code: it pulls the matching nodes into each prompt and rebuilds the graph in the background after every turn. No daemon, no re-indexing to remember, nothing to run or maintain by default — the graph is just files. Nothing is written until you pick. Run graft init --dry-run to see every file it would touch…
The latest refresh did not succeed. This is the last available preview; check the original for changes.
Read the full README ↗ · Preview checked 2026-10-13T05:24:03.979Z
Inside the original README — Document outline
- Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextua
- Up to 4× cheaper and 3× faster, with better or no loss of correctness.
- Contents
- Quick start
- The problem
- What Graft does
- Benchmark
- SWE-bench Verified
- How the graph gets built
- Supported languages
- What's in a node
- What runs where
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
Repository facts
- Owner
- trailhq
- Primary language
- TypeScript
- Stars
- 9,944
- Forks
- 879
- Open issues + pull requests
- 241
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2026-07-03T13:44:21.000Z
- Last push
- 2026-10-13T11:47:51.000Z
Topics and intended use
Owner-supplied topics: ai-agents, anthropic, claude-code, cli, code-graph, codex, context-engineering, cursor, developer-tools, gemini, knowledge-graph, llm, mcp, mcp-server, open-source, openai, tree-sitter
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-13T12:11:02.172Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.