🧠 The Neural Backbone for Autonomous AI Agents

Bridge the gap between your codebase and your AI editor. CCM transforms static source code into a dynamic, queryable Knowledge Graph, enabling AI agents to navigate, understand, and reason about your project with surgical precision.

Modern AI coding assistants (Claude, Cursor, Windsurf) are powerful but suffer from blindness:

CCM turns your AI from a text predictor into a Senior Architect.

Unlike tools that dump raw code, CCM injects AI-Optimized Context:

• Logical Reasoning - Explains why code was retrieved
• Relational Edges - Maps how files talk to each other
• Confidence Scores - Shows certainty in results

• Two-Pass Indexing - Links function definitions to call sites
• Deep Traversal - Ask "Who calls this?" and get accurate answers

• Rust-Powered - Blazing fast indexing and queries
• Batch Embedding - Thousands of lines in seconds
• LanceDB - Millisecond-latency vector storage
• Tree-sitter - Robust AST for Rust, Python, TypeScript

• Binary Checksums - Release artifacts include checksums.txt for integrity
• MCP Allowlist - Restrict project access with CCM_ALLOWED_ROOTS
• Safe Defaults - Configurable timeouts and file-size limits

• Plug & Play - Works with Claude Desktop, Antigravity, Zed, Cursor
• Lazy Indexing - Auto-indexes on first query
• Zero-Config - Auto-detects project root

# 1. Configure MCP for your AI editor
npx @senoldogann/context-manager install

# 2. Index your project
npx @senoldogann/context-manager index --path .

git clone https://github.com/senoldogann/LLM-Context-Manager.git
cd LLM-Context-Manager
cargo build --release

# Binary location: target/release/ccm-cli

Create ~/.ccm/.env:

# Option A: Local (Recommended - Privacy)
EMBEDDING_PROVIDER=ollama
EMBEDDING_HOST=http://127.0.0.1:11434
EMBEDDING_MODEL=mxbai-embed-large

# Option B: Cloud (OpenAI)
EMBEDDING_PROVIDER=openai
EMBEDDING_API_KEY=sk-your-key
EMBEDDING_MODEL=text-embedding-3-small

# Networking & Limits
EMBEDDING_TIMEOUT_SECS=30
CCM_MAX_FILE_BYTES=2097152

# MCP Security
CCM_ALLOWED_ROOTS=/Users/you/projects:/Users/you/sandbox
CCM_REQUIRE_ALLOWED_ROOTS=0

# MCP Runtime
CCM_MCP_ENGINE_CACHE_SIZE=8
CCM_MCP_DEBUG=0

# Optional: disable embeddings entirely (semantic search disabled)
CCM_DISABLE_EMBEDDER=0

# Optional: embed data files (md/json/yaml) into vector search
CCM_EMBED_DATA_FILES=0

# npm wrapper security (0 = enforce checksum, 1 = bypass)
CCM_ALLOW_UNVERIFIED_BINARIES=0

Note: Requires Ollama running (ollama serve) with model pulled (ollama pull mxbai-embed-large). Production Tip: Set CCM_ALLOWED_ROOTS and enable CCM_REQUIRE_ALLOWED_ROOTS=1 to prevent unintended project access.

# Index a project
ccm-cli index --path .

# Search semantically
ccm-cli query --text "authentication logic"

# Cursor prediction (file:line format)
ccm-cli query --text "src/main.rs:50"

# Watch mode - auto-reindex
ccm-cli index --path . --watch

# Evaluate retrieval quality
ccm-cli eval --tasks eval/golden_tasks.json

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│ AI Agent    │────▶│ MCP Server  │────▶│ Core Engine │
│ (Claude)    │◀────│ (ccm-mcp)   │◀────│ (Rust)      │
└─────────────┘     └─────────────┘     └─────────────┘
                                                  │
                    ┌────────────────────────────┼────────────────────────────┐
                    ▼                            ▼                            ▼
             ┌─────────────┐            ┌─────────────┐            ┌─────────────┐
             │ Code Graph  │            │  Vector DB  │            │  Parser     │
             │ (Petgraph)  │            │  (LanceDB)  │            │(Tree-sitter)│
             └─────────────┘            └─────────────┘            └─────────────┘

CCM includes a golden task evaluation framework:

# Run evaluation
ccm-cli eval --tasks eval/golden_tasks.v3.ccm.json

# Compare structural vs hybrid scoring
ccm-cli eval --tasks eval/golden_tasks.json --compare

Latest Results: 100% pass rate on golden tasks.

1. Run ccm-cli index --path . first
2. Check CCM_PROJECT_ROOT matches indexed directory
3. Ensure Ollama is running

• First run downloads embedding model (~1.5GB)
• Subsequent runs are fast (incremental)

1. Ensure the GitHub Release includes checksums.txt
2. Re-run the install once
3. As a last resort, set CCM_ALLOW_UNVERIFIED_BINARIES=1 to bypass verification

• Set CCM_ALLOWED_ROOTS to include the project root
• Or disable strict mode with CCM_REQUIRE_ALLOWED_ROOTS=0

• Increase CCM_MAX_FILE_BYTES if you need larger text files indexed

• By default, data files (.md, .json, .yaml) are indexed but not embedded.
• Enable CCM_EMBED_DATA_FILES=1 to include them in semantic search.

• NPM Package: @senoldogann/context-manager
• Getting Started: GETTING_STARTED.md
• Contributing: CONTRIBUTING.md

MIT License - Open source and free to use.

SENOL DOGAN ❤️