claude-context vs Graft

claude-context is much bigger: 12.5k stars against 5.6k. Over the days we have tracked them claude-context moved +6% and Graft +1199.3%, so Graft is growing faster right now.

Graft leads on setup ease. claude-context 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

An MCP plugin that gives Claude Code whole-repo semantic code search via hybrid BM25 + dense vector retrieval backed by Milvus, reducing tokens compared with loading large directories into the model.

Stars
12.5k
Tracked growth
+6%
Maturity
Last commit
52d ago
Language
TypeScript
License
MIT
Cost to run
Requires OpenAI and Zilliz Cloud (Milvus) API keys.

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.
0%+1199%88 tracked days
zilliztech/claude-contextNanoNets/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.

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

Which one to pick

Pick claude-context if…

Cost-effective — provides whole-repo semantic retrieval (hybrid BM25 + dense embeddings) as an MCP server to give deep context to Claude Code while lowering token usage.

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

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.

  • Setup ease: One-command init (5/5 against 3/5)
Runs in cli, ide, coding-agent-plugin, ci. Works with byok, openai, anthropic.

What people want from each one

Questions people ask

Is claude-context better than Graft?

Graft leads on setup ease. claude-context does not take any axis by a clear margin. claude-context is worth picking when cost-effective — provides whole-repo semantic retrieval (hybrid BM25 + dense embeddings) as an MCP server to give deep context to Claude Code while lowering token usage.

Which of claude-context and Graft keeps my code private?

claude-context: Cloud APIs (your keys) (3/5). Graft: Self-hostable (4/5).

What does each one cost to run?

claude-context: Requires OpenAI and Zilliz Cloud (Milvus) API keys.. Graft: Your API key; provider billing applies..

Full profiles: zilliztech/claude-context and NanoNets/Graft. Everything else in Codebase context.