Uteke

[Uteke owl logo]

Uteke

Long-term memory for any AI agent.
One Rust binary, runs offline, no API key. Self-host it free, or let us host it on Uteke Cloud.

[CI] [Latest Release] [License: Apache 2.0] [GitHub Stars] [Docker Hub pulls] [GitHub release downloads] [LongMemEval-S recall@5: 98.2%]

Quick start · Benchmarks · Connect your agent · Docs · Uteke Cloud · Bahasa Indonesia

[LongMemEval-S, 500 questions, Uteke v0.20.0: recall_any@5 98.2%, strict recall_all@10 95.2%, coverage@5 94.4%, strict recall_all@5 88.0% (max possible 99.4%). Keyword search alone 91.4% vs Uteke's fused default 98.2%.]

All 500 LongMemEval-S questions, no LLM call in retrieval. Raw outputs are committed: check them in a minute, or re-run everything for about $10.

Why Uteke

On Monday you tell your agent how you deploy. By Thursday it has no idea. Every session starts from zero, and every agent keeps its own half-memory.

Uteke gives all of them one long-term memory that runs on your own machine:

• Verifiable recall. 98.2% recall@5 on LongMemEval-S, with the stricter numbers shown next to it and the raw outputs in this repo.
• Fast and cheap to query. ~45 ms warm recall, 0 LLM tokens per query, CPU only.
• One binary. No Python, no Docker, no vector database, no API key. The embedding model (~200 MB) downloads once.
• One memory, every agent. Claude Code, Claude Desktop, Cursor, Codex, Hermes and any MCP client share the same store. Rooms record which agent or person wrote what.
• Finds by meaning and by keyword. Local vectors and SQLite full-text search, fused into one ranking (how it works).
• Remembers over time. Point-in-time recall (--at), a relationship graph, a document engine, and decay for stale memories.
• Private by default. No telemetry. Secrets such as API keys are masked before a memory is stored.
• Open source. Apache-2.0, cosign-signed releases.

Quick start

# Install (macOS Apple Silicon, Linux; Windows: see below)curl -sSL codecora.dev/uteke/install | sh
# Store a memoryuteke remember "Deploy v2.1 to staging at 3pm"
# Search it back: by meaning AND by keyworduteke recall "when do we deploy?"
# Look at what is stored, in a read-only browser pageuteke view

[Terminal demo: uteke remember stores two notes, then uteke recall 'which port is the database on?' returns the Postgres port note and 'what is our release process?' returns the deploy note, with no shared keywords.]

No API keys, no Python, no cloud account. The first run downloads the embedding model (~200 MB, one time).

Give your agent (Claude Code, Cursor, Hermes) the same memory with one line:

// .mcp.json{ "mcpServers": { "uteke": { "command": "uteke-mcp" } } }

New to Uteke, or you are an AI agent? Run uteke onboard. It detects your setup, asks which agent you use, and wires it up. 📖 Onboarding

Rather not run anything locally? Uteke Cloud runs the same engine for you: add one URL to Claude, sign in, done. Free during the open beta.

Self-host or Cloud

Same engine, two ways to run it.

Choose self-host if your data must stay on your machine, or you want to run Uteke inside your own infrastructure. Choose Cloud if you want one memory across several devices and agents without running a server.

Benchmarks

LongMemEval-S (ICLR 2025) hides the facts an agent needs across ~115 chat sessions per question and checks whether retrieval finds them. 500 hand-curated questions, five memory abilities. Uteke runs the full suite with zero LLM calls in the retrieval path: local embeddings, one CPU, deterministic.

[LongMemEval-S recall_any@5, 500 questions: Uteke 98.2%, MemPalace 96.6%, agentmemory 95.2%. Axis starts at 0.]

_{¹ Their published numbers on the same benchmark and 500-question split, on their own recall_any@5 basis (head-to-head notes); evaluation setups differ. ² Strict = every gold session in the top 5; 65% of questions have more than one. Max possible 99.4%. ³ agentmemory publishes MRR 88.2%, which is a different metric.}

🎯 Don't trust our benchmark. Run it yourself. Public dataset, committed raw outputs for every validated release, scoring you can recompute in ~20 lines of Python. Verifying the committed results takes a minute and needs no embedder; re-running all 500 questions costs about $10. 👉 benchmarks/longmemeval/REPRODUCING.md · 🧾 Receipts for the headline number (v0.19.0 run)

LoCoMo. LoCoMo end-to-end QA measures answer accuracy, and the result depends on the LLM answerer and the LLM judge used. In an internal comparison, identical answers were scored up to 8 points apart when only the judge model was swapped. For that reason we do not publish a single LoCoMo number in this README. The full table, the per-judge figures and the receipts are in benchmarks/locomo/RESULTS.md. Retrieval recall, which needs no judge, remains the metric we rely on.

uteke bench --counts 100,1000,10000 measures latency and throughput on your own machine. 📖 Benchmark docs

Connect your agent

# Create a shared roomuteke room create engineering --title "Team decisions"
# Alice's agent stores a decisionuteke remember "We chose Redis for caching over Memcached" \  --room engineering --author alice
# Bob's agent adds contextuteke remember "Redis cluster: 3 nodes, 2 replicas each" \  --room engineering --author bob
# Any agent can recall the shared historyuteke room recall engineering "caching decision"

Features

How it works

graph LR    Input[Query] --> Embed[Local embedder<br/>EmbeddingGemma Q4, 768d]    Input --> FTS5[Full-text search<br/>SQLite FTS5]    Embed --> Vec[Vector index<br/>usearch or vecq]    Vec --> Hybrid[Hybrid<br/>vector + FTS5, RRF k=60]    FTS5 --> Hybrid    Vec --> Fusion[Fusion<br/>vector x1.7 + hybrid x1]    Hybrid --> Fusion    Fusion --> Boost[Salience + recency]    Boost --> Results[Ranked results]
    style Input fill:#131A15,color:#F3F8F4    style Fusion fill:#1F908C,color:#fff    style Results fill:#0B6667,color:#fff

1. Vector index finds by meaning ("deploy" matches "rollout").
2. FTS5 finds by exact terms ("deploy" matches "deploy").
3. Hybrid merges the two lists with Reciprocal Rank Fusion (k=60).
4. Fusion merges the vector ranking (weight 1.7) with the hybrid ranking (weight 1), then adds small salience and recency boosts.

Everything runs in-process: no network, no server required. --strategy vector | fts5 | hybrid | graph picks a single stage instead.

docker run -d -p 127.0.0.1:8767:8767 -v uteke-data:/data codecoradev/uteke:latest --host 0.0.0.0# or, without Docker: uteke-serve --port 8767

Compared with other memory tools

Documentation

FAQ

Contributing

cargo build --workspace                                # Buildcargo test --workspace                                 # Testcargo clippy --workspace --all-targets -- -D warnings  # Lintcargo fmt --all                                        # Format

Contributions welcome. Read CONTRIBUTING.md for the full guide, or say hi in Discussions.

License

Apache License 2.0. Use it, fork it, ship it.

[Uteke star history]

If Uteke helps your agents remember, a ⭐ helps other people find it.