Index codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Linux kernel (28M LOC, 75K files) in 3 minutes. RAM-first pipeline with LZ4 compression and in-memory SQLite.
Single static binary for macOS, Linux, and Windows. No Docker, no runtime dependencies, no API keys.
Vendored tree-sitter grammars compiled into the binary. Nothing to install, nothing that breaks.
5 structural queries consume ~3,400 tokens vs ~412,000 via file-by-file search. One graph query replaces dozens of grep/read cycles.
Auto-detects Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, OpenClaw, and Kiro.
3D interactive UI at localhost:9749 (optional UI binary variant).
Built-in 3D graph visualization (UI variant) — explore your knowledge graph at localhost:9749
curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash
curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash -s -- --ui
# 1. Download the installer
Invoke-WebRequest -Uri https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.ps1 -OutFile install.ps1
# 2. (Optional but recommended) Inspect the script
notepad install.ps1
# 3. Run it
.\install.ps1
| Operation | Time | Notes |
|---|---|---|
| Linux kernel full index | 3 min | 28M LOC, 75K files → 4.81M nodes, 7.72M edges |
| Linux kernel fast index | 1m 12s | 1.88M nodes |
| Django full index | ~6s | 49K nodes, 196K edges |
| Cypher query | <1ms | Relationship traversal |
| Name search (regex) | <10ms | SQL LIKE pre-filtering |
| Dead code detection | ~150ms | Full graph scan with degree filtering |
| Trace call path (depth=5) | <10ms | BFS traversal |
All binaries scanned by 70+ antivirus engines. Zero detections required to publish.
Cryptographic build provenance generated by GitHub Actions. Verifiable artifacts.
All processing happens 100% locally. Your code never leaves your machine.
Open source with permissive licensing. Full source available for audit.