RepoWeaver

Code context fabric for AI coding agents — deterministic call-graph indexing, hybrid retrieval, and a single-tool MCP interface.

RepoWeaver builds a local, zero-cost code intelligence layer that lets AI coding agents (Codex, Claude Code, CodeWiz, etc.) answer structural questions without reading entire files.

"Who calls this method, and what would break if I change its signature?"
→ explore(query, task="impact", repo=".", max_tokens=4000)
→ [verbatim source slices + call paths + blast radius + known blind spots]

Why

AI agents that rely on grep or full-file reads waste tokens and miss cross-file call chains. Existing tools either require cloud APIs, embed LLMs in the index layer, or carry restrictive licenses. RepoWeaver takes only the verified-consensus patterns from the landscape and assembles them locally.

Design

Six primitives, all independently validated across multiple open-source tools:

Not included: LLM in the index layer (rejected by every serious tool), code sent to external APIs, opinionated semantic summaries.

Roadmap

Each milestone ships a fabric verify --level mN gate that runs in CI.

Verification approach

Benchmarks use public repos only — no proprietary code enters this repository.

Install (coming in v0.1.0)

pip install repoweaver
fabric build          # index current repo, $0, no LLM
fabric init           # inject AGENTS.md protocol + edit hook
fabric verify --level m1

MCP tool

explore(
  query: str,
  task: "understand" | "impact" | "locate" | "debug",
  repo: str = ".",
  max_tokens: int = 4000
) → {
  slices: [{file, span, source}],
  call_paths: [...],
  blast_radius: [...],
  blind_spots: "DI / reflection / MQ edges not represented"
}

Acknowledgements

Design patterns drawn from (not forked from): CodeGraph · Graft · GitNexus · Serena · SCIP · Aider

License

MIT