workflowstacks
local-ai

uteke: AI Memory Engine

Store and recall AI memories offline with uteke. For founders building local AI tools.

From the repo · “🧠 The Brain for Your AI — Local-first memory engine for AI agents. Store, recall, and search memories with semantic embeddings. Single Rust binary, zero config, fully offline.”

275 stars+4★ this week31 forksRustGuide quality 9/10 · reviewed Jul 17Updated 10/22/2026100% free · open source
What it does

Uteke is a local-first memory engine that allows founders to store, recall, and search AI memories offline with semantic embeddings.

When to use it
  • •When building local AI tools that require offline memory storage
  • •When developing AI agents that need to recall and search memories without internet connection
  • •When working with sensitive data that cannot be stored online
Ready-to-paste prompt
uteke add my_memory --memory 'This is a test memory with semantic embedding' --embedding '[0.1, 0.2, 0.3]'
Heads up: Make sure to handle errors and edge cases when working with semantic embeddings, as the embedding format and dimensions must match the expected input format for uteke to work correctly
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/uteke && curl -fsSL https://workflowstacks.com/api/skills/uteke/claude-skill -o ~/.claude/skills/uteke/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How uteke: AI Memory Engine works
Codeflow
Free to inspect

Uteke: AI Memory Engine is a very large Rust project (~84k lines across 167 code files, plus 9 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~84k lines · 167 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Rust · Docker
No API keys detected
Rust 92%Python 4%Shell 2%Go Template 1%TypeScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENT.md
    The instructions the AI actually follows
  3. 3
    Cargo.toml
    Dependencies and the commands it exposes
  4. 4
    examples/python_uteke.py
    A worked example — copy this to get going
What's in each folder
extensions/Sub-packages / plugins7 files
integrations/Sub-packages / plugins3 files
docs/Documentation45 files
examples/Examples you can copy2 files
crates/Folder157 files
benchmarks/Evaluations & benchmarks40 files
scripts/Helper scripts13 files
.github/CI / automation (GitHub Actions)14 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
codecoradev
Language
Rust
Category
local-ai
Published
5/29/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/uteke.svg)](https://workflowstacks.com/skills/uteke?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Related skills

More local-ai tools founders pair with this one.

local-ai★ 132,041
Run Powerful LLMs Locally with llama.cpp – Fast C++ Inference
Empower your product with on‑device LLM inference using llama.cpp’s efficient C++ engine. Ideal for founders who need privacy, speed, and no cloud costs. 130k+ GitHub stars.
local-ai★ 94,719
Stirling-PDF: Edit PDFs Anywhere
Edit PDFs on any device with Stirling-PDF, a tool for startup founders, backed by 80k+ GitHub stars
local-ai★ 38,243
Run AI Locally with llmfit
Find compatible AI models for your hardware with llmfit, a tool for founders, with 29k+ GitHub stars.
local-ai★ 18
agent-chief: Keep Founder Focus by Filtering Interruptions Locally
For founders juggling AI agents, alerts, and feeds, agent-chief runs locally to decide when to interrupt, preserving your most limited resource—attention.
local-ai★ 492
xybrid: Deploy On‑Device AI Apps Quickly for Mobile & Edge
xybrid lets founders ship privacy‑first AI features to iOS, Android and Unity apps using Rust, Swift or Kotlin—ideal for edge and game developers.
local-ai★ 30,526
koreader: Multi-format eBook Reader
Get a versatile eBook reader for various devices. For founders needing eBook solutions, backed by 28k+ GitHub stars.