Graft vs Graft

The two are close in size: 5.6k stars for Graft, 5.6k for Graft.

Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work.

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

Persists a deterministic, human-readable context graph as markdown files inside the repo (no embeddings or external index), so agents can follow real files and share an up-to-date code understanding via git.

Stars
5.6k
Tracked growth
+1199.3%
Maturity
Last commit
1d ago
Language
TypeScript
License
MIT
Cost to run
Your API key; provider billing applies.

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
5.6k
Tracked growth
not tracked long enough
Maturity
Last commit
1d ago
Language
TypeScript
License
MIT
Cost to run
Your API key, per-use
0%+1199%38 tracked days
NanoNets/Grafttrailhq/Graft

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.

AxisGraftGraft
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 graph
Whole-repo analysis
Noise control
How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only.
Ranking & checks
Minimal filters
Customization
How far it bends to your team: custom rules, prompts, style guides, per-path config.
Config & flags
Config options
Privacy
Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only.
Self-hostable
Fully local possible
Model freedom
Whether you can point it at any provider, or it is wired to one.
Bring-your-key
Bring-your-own-model
Setup ease
What it takes to get a first useful run out of it.
One-command init
Two-command setup

Which one to pick

Pick Graft if…

Easy setup — one-command init builds a local, versionable code-graph and wires directly into coding agents (Claude Code et al.) to cut tokens, tool calls, and latency.

Runs in cli, ide, coding-agent-plugin, ci. Works with byok, openai, anthropic.

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.

Runs in cli, coding-agent-plugin, ide. Works with byok, openai, anthropic, local-ollama, other-fixed.

What people want from each one

Questions people ask

Is Graft better than Graft?

Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work. Graft is worth picking when easy setup — one-command init builds a local, versionable code-graph and wires directly into coding agents (Claude Code et al.) to cut tokens, tool calls, and latency.

Which of Graft and Graft keeps my code private?

Graft: Self-hostable (4/5). Graft: Fully local possible (5/5).

What does each one cost to run?

Graft: Your API key; provider billing applies.. Graft: Your API key, per-use.

Full profiles: NanoNets/Graft and trailhq/Graft. Everything else in Codebase context.