Uteke

Give your AI a memory that never leaves your machine.

Your AI forgets everything between sessions. Uteke fixes that — one binary, fully offline, ~45ms recall.

🇬🇧 English · 🇮🇩 Bahasa Indonesia

⚡ 30-Second Quick Start

# Install (macOS, Linux, Windows)
curl -sSL codecora.dev/install | sh

# Store a memory
uteke remember "Deploy v2.1 to staging at 3pm"

# Search it back — by meaning, not just keywords
uteke recall "when do we deploy?"

That’s it. No API keys. No Docker. No Python. No cloud.

First run downloads the embedding model (~188MB, one-time) and you’re running.

Want richer memories? Add metadata:

uteke remember "Deploy v2.1 to staging" \
  --tags deploy,staging \
  --entity staging-server \
  --category infrastructure

🚀 Onboarding (New users & AI agents)

Are you an AI agent reading this? Your user just shared this repo link with you.
Run uteke onboard to interactively configure uteke for your environment — it will
detect your install, ask which agent you are, toggle features, write config, and
show you every command available. If non-interactive: uteke onboard --yes --agent <your-agent>.

New to uteke? One command takes you from zero to productive:

uteke onboard

The wizard will:

1. Detect if uteke is installed and if a store exists
2. Ask which AI agent you use (Hermes, Claude, Cursor, Pi, OpenCode)
3. Pick integration mode — manual tool calls vs automatic memory-provider
4. Toggle features on/off (Aging, Auto-maintenance, Graph rerank, Salience/Recency boost, Server mode)
5. Write ~/.uteke/uteke.toml with your selections
6. Install agent integration files automatically (uteke init)
7. Showcase every uteke command grouped by category

Non-interactive (CI, scripts, AI agents):

uteke onboard --yes --agent hermes --namespace default

📖 Full onboarding docs · CLI reference

🔥 Why Uteke?

You just spent 2 hours explaining your codebase to ChatGPT. Next session? Blank slate. Again.

Every AI tool forgets. Context windows fill up, sessions end, and your AI starts over every single time. Uteke gives it persistent memory — and keeps it on your machine.

Uteke vs Mnemosyne: Both are local-first with semantic + FTS5 search. Mnemosyne is the closest competitor (~1.5K stars, Python). Uteke wins on single binary (no Python runtime), rooms, time-travel queries, and zero runtime dependencies.

Uteke vs Engram: Both are single-binary, offline, no-API-key tools. But Engram is FTS5-only (keyword search). Uteke adds vector semantic search + RRF fusion + rooms + time-travel + graph relationships + smart decay + document engine + batch import. Same simplicity thesis, 10× the features.

Uteke vs AgentMemory/Mem0/Letta/Zep: Those are powerful — but all require cloud LLM API keys and Docker infrastructure. Your data goes to OpenAI/Anthropic. Uteke runs fully offline with local ONNX embeddings. No Docker, no Python, no API keys.

💡 What Can You Do With Uteke?

🤖 Building AI agents? Give them persistent memory without cloud dependencies. Your agent remembers user preferences, past decisions, and context — across sessions, fully offline.

👥 Working in a team? Use Rooms to share knowledge. Meeting notes, project decisions, architecture choices — searchable by everyone, attributed by author.

🔒 Building for privacy-sensitive domains? Healthcare, finance, legal — data stays on your machine. No API calls, no telemetry, no cloud. Local embeddings (ONNX, 768d).

⌨️ Power user who lives in the terminal? Uteke is your personal knowledge graph. Remember anything, recall by meaning, link related thoughts. All from the command line.

✨ Features

Core Memory

Search & Intelligence

Integrations

Performance & Privacy

// .mcp.json (Claude Code, Cursor)
{ "mcpServers": { "uteke": { "command": "uteke-mcp" } } }

📖 Full documentation · CLI reference · Configuration

🏗️ Architecture

graph LR
    Input[User Query] --> Embed[Local ONNX Embedder<br/>768d, EmbeddingGemma Q4]
    Embed --> HNSW[HNSW Vector Index<br/>usearch]
    Embed --> FTS5[FTS5 Full-Text<br/>SQLite]
    HNSW --> RRF[Reciprocal Rank Fusion<br/>k=60]
    FTS5 --> RRF
    RRF --> Results[Ranked Results]

    style Input fill:#4a9eff,color:#fff
    style Results fill:#4aff9e,color:#000
    style RRF fill:#ff9e4a,color:#fff

How hybrid search works:

1. HNSW (usearch) — finds by meaning (“deploy” matches “rollout”)
2. FTS5 (SQLite) — finds by exact terms (“deploy” matches “deploy”)
3. RRF (k=60) — merges both ranked lists → best of both worlds

Everything runs in-process. No network. No cloud. No server required (unless you want server mode).

❓ FAQ

🤝 Contributing

cargo build --workspace        # Build
cargo test --workspace         # Test (206 tests)
cargo clippy -- -D warnings    # Lint
cargo fmt                      # Format

Contributions welcome! Read CONTRIBUTING.md for the full guide.

📄 License

Apache License 2.0 — use it, fork it, ship it.

⭐ Star History

Found this useful? ⭐ Star this repo — it helps others discover Uteke.