ripwire vs Graft
Graft is much bigger: 9.7k stars against 2.4k. Over the days we have tracked them ripwire moved +165.1% and Graft +99.2%, so ripwire is growing faster right now.
ripwire leads on noise control. Graft does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
A zero-dependency, fully local CLI that produces a ranked, token-budgeted call-graph and blast-radius map with disclosed uncertainty and deterministic results, avoiding index servers and heavy token costs.
- Stars
- 2.4k
- Tracked growth
- +165.1%
- Maturity
- ●●●●●
- Last commit
- 2d ago
- Language
- C++
- License
- Apache-2.0
- Cost to run
- Free, local binary
Writes a readable, linked markdown graph of your code (no embeddings or external index), letting agents use a local, regenerable map rather than re-exploring the repo each run.
- Stars
- 9.7k
- Tracked growth
- +99.2%
- Maturity
- ●●●●●
- Last commit
- 6m ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Your API key, per-use
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | ripwire | Graft |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Whole-repo analysis | ●●●●● Whole-repo analysis |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Confidence & disclosure | ●●●●● Minimal filters |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● CLI options & grammars | ●●●●● Config options |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Fully local | ●●●●● Fully local possible |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Provider-agnostic | ●●●●● Bring-your-own-model |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-line install | ●●●●● Two-command setup |
Which one to pick
Pick ripwire if…
Privacy-first — run a single self-contained binary offline to get a ranked, token-efficient map of your repo without sending code to the cloud.
- Noise control: Confidence & disclosure (4/5 against 2/5)
Pick Graft if…
Efficiency-first — pick Graft when you want much faster and cheaper agent runs (often with equal or better correctness) by providing a repo-wide local node graph that agents can read directly.
What people want from each one
redhat-et/ripwire
trailhq/Graft
Questions people ask
Is ripwire better than Graft?
ripwire leads on noise control. Graft does not take any axis by a clear margin. ripwire is worth picking when privacy-first — run a single self-contained binary offline to get a ranked, token-efficient map of your repo without sending code to the cloud.
Which of ripwire and Graft keeps my code private?
ripwire: Fully local (5/5). Graft: Fully local possible (5/5).
What does each one cost to run?
ripwire: Free, local binary. Graft: Your API key, per-use.
Full profiles: redhat-et/ripwire and trailhq/Graft. Everything else in Codebase context.