claude-context-compiler 0.2.0

Local context compiler for AI coding assistants — smallest correct context bundle with rationale

context-compiler

A local-first MCP server that indexes your Python and TypeScript codebase into a dependency graph and returns the smallest correct context bundle for any coding task — with a one-line rationale for every included file.

No cloud. No LLM API calls. No data leaves your machine.

---

The problem

When you ask Claude to fix a bug or add a feature, it reads files by guessing which ones are relevant. It over-reads (wastes tokens) or misses the file that actually matters. The bigger the codebase, the worse this gets.

How it works

Your task: "fix the keycloak token expiry"
         ↓
  Classify → BUG_FIX
         ↓
  Find entry nodes → keycloak.py (BM25 + docstring matching)
         ↓
  Traverse graph → keycloak.py + secured_view.py + test_keycloak_steps.py
         ↓
  Score + budget → 870 tokens (within 8000 limit)
         ↓
  Return bundle with rationale per file

Everything — classification, traversal, scoring, rationale — is deterministic. Same repo + same task = same bundle, every time.

---

Installation

# cd into your project, then:

# Index the current directory
uvx claude-context-compiler index

# Preview what context a task would produce
uvx claude-context-compiler explain --task "fix the retry logic"

# Start the MCP server (Claude Code does this automatically)
uvx claude-context-compiler serve

All commands default to the current directory. Pass --repo <path> to target a different directory.

Requires Python 3.11+.

Optional: semantic fallback

Install the optional fastembed model (23MB ONNX, no PyTorch) for better matching when task terms don't appear in symbol names:

pip install "context-compiler[semantic]"

---

Claude Code integration

1. Index your repo and register the MCP server:

cd /path/to/your/repo
uvx claude-context-compiler index
claude mcp add --scope user context-compiler uvx -- claude-context-compiler serve --repo /path/to/your/repo

2. Add to your repo's CLAUDE.md:

## Context retrieval

Before reading any source files, call `get_context` with the task description.
Read only the files it returns.

3. Use it:

> Fix the keycloak token expiry bug

Claude calls get_context("fix the keycloak token expiry bug"), gets back the exact files to read, and starts working — no guessing.

---

MCP tools

get_context(task, budget=8000)

Returns the minimal file bundle for a coding task.

{
  "files": ["admin/keycloak.py", "admin/views/secured_view.py"],
  "rationale": [
    "Included Keycloak as primary task location (matched 'keycloak')",
    "Included SecuredView._has_role because it is called by Keycloak (depth 1)"
  ],
  "token_estimate": 870,
  "tokens_saved": 0,
  "task_type": "BUG_FIX",
  "confidence": 1.0
}

refresh(changed_files)

Re-indexes the repository after file changes.

---

What makes it different

Task-type-aware traversal. A bug fix traverses inbound callers and test coverage at depth 2. A new feature traverses imports and sibling modules. A refactor traverses everything at depth 3. No other tool adjusts retrieval strategy based on what you're actually trying to do.

Rationale per file. Every included file has a one-line explanation of why it's there. You can see what Claude will read before it reads it.

Hard token budget. The bundle never exceeds the limit. Partial file inclusion is not permitted.

Local-first. Embedded KuzuDB graph, no server, no port, no auth. Works offline.

---

Supported languages

Language	Parsing	Docstrings
Python	tree-sitter-python	✓ (first line of docstring)
TypeScript / TSX	tree-sitter-typescript	✓ (JSDoc /** */)

---

Environment variables

Variable	Default	Description
CC_REPO_PATH	required	Path to indexed repository
CC_TOKEN_BUDGET	8000	Default token budget for get_context

---

Tech stack

tree-sitter · KuzuDB · BM25 (rank-bm25) · rapidfuzz · FastMCP · fastembed (optional)

---

License

Apache 2.0