AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
RAG / Knowledge Base/
uteke
uteke logo

uteke

Active·★ 275·Apache-2.0·Updated 2026-10-22
★ Hidden Gem

Uteke provides a persistent, private memory layer for AI agents that operates entirely offline without cloud dependencies or API keys. It enables agents to remember context, past decisions, and preferences across sessions, leveraging hybrid search and multi-agent shared memory.

uteke sits in the RAG / Knowledge Base category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Hybrid Search (Vector similarity + FTS5 full-text search, merged by Reciprocal Rank Fusion). A representative use case is Building AI agents (Give them persistent memory without cloud dependencies). The listed license is Apache-2.0. GitHub stars are currently 275. Relevant tags include AI Memory, Persistent Context.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#AI Memory#Persistent Context#Offline AI#Hybrid Search#Multi-Agent#Knowledge Base#Local Embeddings#Privacy-first
$ Install
$ curl -sSL codecora.dev/uteke/install | sh
↗ Visit site★ GitHub
01

Features

01Hybrid Search (Vector similarity + FTS5 full-text search, merged by Reciprocal Rank Fusion)
02Rooms (Multi-agent shared memory with author attribution)
03Time-travel (Recall memories as they existed at any point in time)
04Single Binary / Fully Offline (Zero dependencies, local ONNX embeddings, no API keys)
05MCP Server (JSON-RPC over stdio + Streamable HTTP for AI agent integration)
02

Why choose it

+Hybrid Search (Vector similarity + FTS5 full-text search, merged by Reciprocal Rank Fusion)
+Rooms (Multi-agent shared memory with author attribution)
+Building AI agents (Give them persistent memory without cloud dependencies)
+Supports 4 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

Claude Code, Cursor, Hermes, MCP-compatible agents
AI Agents
Verified via docs
Rust
Language
Verified via docs
macOS, Linux, Windows
OS
Verified via docs
Docker
Containerization
Verified via docs
05

Quick start

1
$ curl -sSL codecora.dev/uteke/install | sh
06

Use cases

↳Building AI agents (Give them persistent memory without cloud dependencies)
↳Working in a team (Share knowledge, meeting notes, project decisions via Rooms)
↳Building for privacy-sensitive domains (Healthcare, finance, legal: data stays on your machine)
↳Power user in the terminal (Personal knowledge graph: remember anything, recall by meaning)
07

Alternatives

⚡Top VS:
VSremnic★228→VSvault-cortex★31→VSmcp-logseq★343→VSedgeever★2.5k→
remnic logo
remnic★ 228
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.
VSCompare→
vault-cortex logo
vault-cortex★ 31
Standalone MCP server for Obsidian vaults — hybrid search, structured memory, tasks, and full vault access for any AI agent
VSCompare→
mcp-logseq logo
mcp-logseq★ 343
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
VSCompare→
edgeever logo
edgeever★ 2.5k
Open-source, AI-native knowledge base & Evernote alternative with native MCP. Zero-cost on Cloudflare or Docker.
VSCompare→
caselaw-repo-1 logo
caselaw-repo-1★ 75
Open Swiss legal corpus + MCP server: 1M+ court decisions (1875–today), 21k laws, 10M-edge citation graph, 42 MCP tools. CC0 data, MIT code. Live at mcp.opencaselaw.ch
VSCompare→
zoteus logo
zoteus★ 61
⚡ The everything Zotero MCP server: complete Zotero Web API v3 + desktop local API for Claude & any MCP client. Search, safe writes, add-by-DOI, CSL citations, hybrid semantic search, and a scholarly-context graph. TypeScript, local-first.
VSCompare→
daidocs logo
daidocs★ 53
Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.
VSCompare→
mxLore logo
mxLore★ 30
Self-hosted MCP server for AI coding assistants. Persistent knowledge base with 45 tools, 12 skills, institutional memory.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
codecoradev /
uteke
↗

🧠 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.

275Apache-2.0
Last commitToday
StatusActive
CategoryRAG / Knowledge Base
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.