Uteke
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
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.
Related MCP server: Mycelia
Quick start
# Install (macOS Apple Silicon, Linux; Windows: see below)
curl -sSL codecora.dev/uteke/install | sh
# Store a memory
uteke remember "Deploy v2.1 to staging at 3pm"
# Search it back: by meaning AND by keyword
uteke recall "when do we deploy?"
# Look at what is stored, in a read-only browser page
uteke viewNo 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.
Method | Command |
Homebrew |
|
Cargo |
|
Docker |
|
Binary | GitHub Releases (macOS, Linux, Windows) |
Windows (PowerShell) |
|
📖 Full install guide · Docker docs
Self-host or Cloud
Same engine, two ways to run it.
Self-host (this repo) | ||
Engine and recall | Full, nothing paywalled | Same engine |
Runs on | Your laptop or your server | Hosted for you |
Connect an agent |
| Add |
Your data | Never leaves your machine | Stored by us; export any time |
Price | Free, Apache-2.0 | Free during the open beta (limits) |
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.
Metric | Uteke v0.20.0 | MemPalace¹ | agentmemory¹ |
recall_any@5 (evidence in top 5) | 98.2% | 96.6% | 95.2% |
recall_any@10 | 98.8% | — | 98.6% |
strict recall_all@5 (all evidence in top 5) | 88.0%² | not published | not published³ |
LLM calls in retrieval | 0 | — | 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.
Stable across releases (full 500 questions, scored from committed raw, RESULTS.md):
Release | v0.16.0 | v0.17.0 | v0.19.0 | v0.20.0 | fix 32a5cf3b |
recall_any@5 | 98.2% | 98.4% | 98.2% | 98.2% | 98.2% |
strict recall_all@5 | 88.0% | 88.0% | 88.0% | 88.0% | 88.0% |
Re-validated 2026-11-08 after the #1690 import fix: strict@5 identical (88.0%), strict@10 +1 question (95.4%), zero misses@50 — four questions shifted partial gold ordering, none lost all evidence.
By question type (recall_any@5, v0.20.0):
knowledge-update | single-session | temporal | multi-session |
100% | 96.7–98.2% | 98.4% | 98.3% |
Every question's evidence lands in the top 50 (zero misses). What's left is ordering when a question needs several sessions at once: strict recall_all@5 is 88.0% against a 99.4% ceiling, and most misses lose exactly one session.
🎯 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
Client | How |
Claude Code |
|
Claude Desktop | |
Cursor | same |
Codex |
|
Hermes | stdio or HTTP · details |
Any MCP client | stdio ( |
Claude on the web, desktop or mobile | add |
No MCP? | any agent that can run a shell command can call the |
# Create a shared room
uteke room create engineering --title "Team decisions"
# Alice's agent stores a decision
uteke remember "We chose Redis for caching over Memcached" \
--room engineering --author alice
# Bob's agent adds context
uteke remember "Redis cluster: 3 nodes, 2 replicas each" \
--room engineering --author bob
# Any agent can recall the shared history
uteke room recall engineering "caching decision"Author attribution on every memory; cross-agent recall without manual sync. 📖 Rooms
Features
Memory | Search | Integrations | Privacy & operations |
Rooms with author attribution | Fusion of vector + full-text (default) | MCP over stdio and Streamable HTTP | Fully offline, no telemetry |
Point-in-time recall ( | Relationship graph and auto-links | Server mode and Docker image | Secrets masked before storage |
Tags, entities, typed memories | Salience and recency boosts | Document engine ( | Signed upgrades (cosign) |
Partial updates and citations | Dream cycle: dedup, backlinks, orphans | Batch import, full export/import | Two vector engines ( |
Core memory
Feature | What it does |
🧠 Hybrid + Fusion Search | Vector similarity + FTS5 full-text search, merged by Reciprocal Rank Fusion (RRF). Since v0.16.0, |
🏠 Rooms | Multi-agent shared memory. Group memories by context (meetings, projects, clients). Multiple agents read/write to the same room with author attribution. Cross-agent recall without manual sync. |
⏳ Time-travel | Recall memories as they existed at any point in time. |
🏷️ Rich Metadata | Tags, entities, categories, key:value pairs on every memory. |
🧩 Memory Types | Typed categories (fact, procedure, decision, etc.) with auto-inference. |
✏️ Partial Updates |
|
📎 Citations | Source attribution on every memory (URL, file, user, import batch). |
👤 Author | Who wrote a memory, with or without a room ( |
🚫 Rejected Values |
|
Search & intelligence
Feature | What it does |
🔗 Relationship Graph | Link memories with typed edges (supersedes, contradicts, references). Auto-backlinks. |
🔗 Cross-Entity Linking | Bidirectional memory↔document references via |
🤖 Cosine Auto-Linking | Automatically creates |
📉 Smart Decay | Composite importance scoring. Pin what matters, let stale memories fade. |
📈 Salience + Recency | Dual-axis recall boost by memory type and age. |
🔍 Orphan Detection | Find disconnected, low-importance memories for cleanup. |
🌙 Dream Cycle | One-command maintenance: lint → backlinks → dedup → orphans. |
🧬 Consolidation | Merge near-duplicate room memories into fewer, denser records: segment-level planner, provenance trust policy, per-pair control. |
Integrations
Feature | What it does |
🔌 MCP Server | JSON-RPC over stdio + Streamable HTTP. Works with Claude Code, Cursor, Hermes. |
🖥️ Server Mode | Persistent daemon: eliminates cold-start embedding load on every call. |
📂 Batch Import | Import entire directories with auto-strategy routing (document vs. memory extraction). |
🪝 Agent Hooks |
|
🎙️ Raw Capture | Queue conversation turns with no LLM call ( |
📝 Document Engine | Wiki/knowledge base with |
📥 Import/Export | JSONL backup and restore; |
🔑 View-Only API Keys | Read-only tokens for safe GET-only access to the server. |
Performance & privacy
Feature | What it does |
📦 Single Binary | Zero dependencies. No Python, no API keys. Local-first by default. |
🐳 Docker Ready | Official multi-arch image on Docker Hub. Run as a shared service for teams or cloud deployments. |
🔒 Fully Offline | Local ONNX embeddings (EmbeddingGemma Q4, 768d). No telemetry, no cloud. The only network call is a daily release check, off with |
🧱 Fenced MCP Output | MCP read tools wrap stored text in |
🛡️ Privacy Filter | Secrets (API keys, tokens, |
✍️ Signed Upgrades |
|
⚡ Recall Cache | LRU cache eliminates redundant embedding for repeated queries. |
🔥 Tiered Memory | Hot/Warm/Cold tracking with auto-cleanup of stale memories. |
🧮 Two Vector Engines |
|
🔄 Embed Fallback | Gracefully degrades to no-op embedder if local model fails (never crashes). |
📊 Benchmarks | Built-in |
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:#fffVector index finds by meaning ("deploy" matches "rollout").
FTS5 finds by exact terms ("deploy" matches "deploy").
Hybrid merges the two lists with Reciprocal Rank Fusion (k=60).
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.
Local-first (default): single binary, zero infrastructure. Your data stays in ~/.codecora/uteke/.
Docker / server mode: for teams or remote agents.
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📖 Docker setup · Server mode · Remote access
Compared with other memory tools
Uteke | Tool A | Tool B | Tool C | Tool D | Tool E | Tool F | Tool G | |
Language | Rust (single binary) | Python (pip) | Python | TypeScript | TypeScript | Python | TypeScript | Go (single binary) |
Setup | One binary ( | pip install + venv | pip + Docker + Qdrant | npm + iii-engine | npm (Node.js) | pip + Docker + Neo4j | Cloud or local binary | One binary |
API keys | ❌ None | ⚠️ For remote embeddings | ✅ OpenAI/LLM | ✅ LLM key | ✅ LLM key | ✅ LLM key | ⚠️ Cloud only | ❌ None |
Works offline | ✅ Fully | ⚠️ Optional | ❌ Cloud embedding | ❌ Needs LLM | ❌ Needs LLM | ❌ Needs LLM + vector DB | ✅ Local binary + Ollama | ✅ Fully |
Search | Fusion (vector + hybrid) | sqlite-vec + FTS5 | Vector + Graph | Vector + Graph | Vector | Hybrid (semantic + keyword + graph) | Vector + rerank | FTS5 only |
Recall speed | ~45ms | ~50ms+ | Network round-trip | Network round-trip | Network round-trip | Network round-trip | Network round-trip | ~Fast (local) |
Multi-agent | ✅ Rooms | ✅ Multi-agent surface | ❌ | ✅ Shared server | ✅ Multi-agent groups | ❌ | ❌ | ⚠️ Shared via MCP |
Time-travel | ✅ Native point-in-time | ⚠️ Temporal triples | ❌ | ❌ | ❌ | ✅ Temporal graphs | ❌ | ❌ |
MCP server | ✅ stdio + HTTP | ✅ stdio + SSE | ❌ | ✅ 54 MCP tools | ❌ | ✅ Graphiti MCP | ✅ Open-source MCP | ✅ stdio MCP |
Your data | ✅ Never leaves machine | ✅ Local-first | ⚠️ Sent to LLM cloud | ✅ Local (iii-engine) | ⚠️ Sent to LLM cloud | ⚠️ Sent to LLM cloud | ⚠️ Cloudflare-hosted | ✅ Local |
License | Apache 2.0 | MIT | Apache 2.0 | Apache 2.0 | Apache 2.0 | Apache 2.0 | MIT | MIT |
Tool labels (A–G) stand for common categories of AI memory layers as of August 2026, assessed from public documentation. Use this as a starting point for your own evaluation, not a ranking.
Documentation
Getting started | |
Reference | |
Concepts | |
Integrations | MCP setup (Claude Code, Claude Desktop, Cursor, Hermes) · Hermes · Claude Code / Codex / Cursor hooks |
Security | SECURITY.md (vulnerability reports, release signing) |
Benchmarks |
FAQ
The engine in this repo is complete and runs fully offline; nothing in it calls the Cloud. Uteke Cloud is a separate, optional hosted service that runs the same engine for people who don't want to run anything locally, and you can export your data from it any time. The open-source engine stays full-capability, and none of the benchmark results above depend on the Cloud.
A file works until you need to find something by meaning: "ship the release" won't match "deploy v2.1" with grep. Uteke searches by meaning and by keyword at once, keeps who wrote each memory, and works the same for every agent you use, instead of one file per tool.
Many memory layers need cloud API keys (OpenAI or another LLM) and extra infrastructure (Docker, Postgres, Qdrant), and your data is sent to an LLM provider. Uteke is a single binary with no API keys; embeddings run locally via ONNX. See the comparison.
Most of them are full-text only (keyword matching). Uteke fuses vector search with full-text search, so you can search by meaning as well as exact words, and adds rooms, time-travel, a relationship graph, decay, a document engine and batch import.
Yes. The embedding model (EmbeddingGemma Q4, 768d) downloads once (~200 MB) on first run. After that, memory operations make no network calls and there is no telemetry. The binaries check GitHub for a new release once a day; set UTEKE_NO_UPDATE_CHECK=1 to turn that off. If the local model fails, Uteke degrades to a no-op embedder; it never calls a cloud API.
~45 ms as a CLI (31 ms average at 10K memories on the published bench host; flat from 100 to 10K memories). No network round-trip, and an LRU cache skips re-embedding repeated queries.
Uteke has 1,300+ tests, mutation testing before each release, CI on every pull request, cosign-signed releases and a benchmark harness. It's used in production by the CodeCora team and other early adopters. It is still 0.x (see the release badge), so expect rough edges, but the core is stable.
Contributing
cargo build --workspace # Build
cargo test --workspace # Test
cargo clippy --workspace --all-targets -- -D warnings # Lint
cargo fmt --all # FormatContributions welcome. Read CONTRIBUTING.md for the full guide, or say hi in Discussions.
License
Apache License 2.0. Use it, fork it, ship it.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Shared AI memory. ChatGPT, Claude, Cursor and any MCP app read and write the same memory.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables persistent memory storage and retrieval for MCP clients, allowing AI assistants to remember facts and context across conversations.26 npmMIT- AlicenseNot gradedqualityDmaintenanceProvides a persistent, cross-tool memory layer for AI coding agents via MCP, enabling storage and retrieval of decisions, preferences, and context across different tools and models.6 npm1MIT
- AlicenseNot gradedqualityCmaintenanceProvides shared long-term memory for AI coding agents via MCP, allowing tools like Claude Code and Codex to store and retrieve distilled facts, notes, and conversation history to persist context across sessions.4 npm3MIT
- AlicenseNot gradedqualityFmaintenanceEnables coding agents to store, retrieve, and share durable memories across projects and machines via MCP, with session-start recall and scoped, versioned storage.23 PyPI6MIT