local-ai

uteke: AI Memory Engine

Store and recall AI memories offline with uteke.
235 stars25 forksRustGuide quality 9/10Updated 8/25/2026100% 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.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

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.

Quick Actions
Details
Creator
codecoradev
Language
Rust
Category
local-ai
Published
5/29/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.