Uteke — Offline Semantic Memory Engine for AI Agents

  uteke remember "Deployed Uteke v0.7.2 to production server"
  Memory stored: id=m_8f3a2c  category=deployment

  uteke recall "what version did we deploy?"
  [1] Deployed Uteke v0.7.2 to production server
      score: 0.94  id: m_8f3a2c  age: 2h

  uteke recall "recent infrastructure changes"
  [1] Migrated Qdrant to port 6333 — new collection  score: 0.89
  [2] Deployed Uteke v0.7.2 to production server    score: 0.85
  [3] Updated Rust toolchain to 1.78 nightly          score: 0.72

  > Ready. 3 memories recalled in 28ms.

Built for Speed & Privacy

Every feature designed around one principle: your data stays local, recalls are instant.

Semantic Search

EmbeddingGemma 768d, hybrid FTS5+vector retrieval

30ms Recall

SQLite + usearch, zero network round-trip

Single Binary

curl install, no Docker, no Python, no Node

MCP Native

27 tools, works with Claude Code, Cursor, Copilot

Local-First

Your data never leaves ~/.uteke/

Auto-Extraction

Session transcripts to structured memories automatically

Quickstart

Three commands. 30 seconds. You're done.

bash

# Install
curl -fsSL codecora.dev/install | sh

# Remember
uteke remember "Deploy v2.1 to staging" --tags deploy

# Recall (30ms)
uteke recall "when did we deploy?"

Architecture

Zero dependencies. Zero network. Pure local.

uteke single binary

│

├──

SQLite structured storage

usearch vector index

EmbeddingGemma 768d ONNX

│

├──

uteke-serve HTTP API :8767

uteke-mcp MCP server · 27 tools

Ready to give your AI a memory?

curl -fsSL codecora.dev/install | sh

Star on GitHub