← Directory

Mem0

Self-hosted memory server for AI coding assistants.

  • AI
  • Databases
  • Development
  • Tools & Utilities
Self-hosted memory server for AI coding assistants. Store, search, and manage persistent context across sessions so your tools remember what happened last week without stuffing everything into the context window. Each project gets its own isolated vector collection with automatic fact extraction, deduplication, and semantic search. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client. Includes a bundled LLM for zero-config operation, or connect to Ollama or OpenAI for better quality. Web dashboard included for browsing and managing memories.

Platform availability

Available on 1 of 9 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

71/100 Good

Maintained
100last commit 4 days ago
Popular
9767,021 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data
Security check
152 serious findings, 6 minor, CI, tests

Based on 4 of 5 factors.

Availability: platform listings confirmed today

GitHub stars
67,021
Open issues
817
Last commit
2026-10-07
Latest release
ts-v3.3.1
License
Apache-2.0
Activity
declining

Checked today - source: GitHub (mem0ai/mem0)

Resources & Compatibility

Requirements not published yet.

Checked 13 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Use the main installer first Run `npx claude-mem install` in a terminal before trying to use the app. It checks dependencies, asks for your AI provider and API key, detects your editor, and installs the hooks and worker; without that, the app has no memory backend to save or search your work. source
  • Use the Cursor/Gemini wizard if applicable If you are setting up Cursor with Gemini, run `bun run cursor:setup` so it can choose Gemini, ask for your API key, and install the needed hooks. This avoids missing provider settings that would stop memory capture from working. source
  • Install Bun if the docs tell you to If you see a `bun` command, install the Bun runtime first, such as `curl -fsSL https://bun.sh/install | bash` on macOS/Linux. Bun is the program that runs those setup and worker commands, so without it the commands will fail. source
  • LLM Backend Runs zero-config with a bundled LLM; optionally connect Ollama or OpenAI for higher-quality fact extraction. source

Fetched today - each note links to its source

Alternatives (7)

  • Claude Memory - Long-term memory for Claude AI.
  • Claude-Mem - A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's…
  • Contextify - Your Claude Code history deletes after 30 days.
  • Engram Alpha - A local-first, open-source long-term graph memory engine for AI agents and developers that actively fights knowledge drift and eliminates c…
  • Mnemosyne OS - A control room for AI memory.
  • Tolaria - Desktop app for large markdown knowledge bases, using plain files, Git versioning, YAML frontmatter, offline use, open source, and Claude C…
  • Tracebrain

Checked today - source: AlternativeTo

Common questions

What Docker services are part of the self-hosted Mem-zero stack?

The self-hosting guide describes a three-container Docker stack: API, Postgres with pgvector, and Neo4j.

Can I use local LLMs with the self-hosted Mem-zero deployment?

Yes, the Docker self-hosting guide says you can swap in local LLMs while keeping conversation data on your own infrastructure.

Does the self-hosted Mem-zero bundle include a web dashboard?

Yes, the self-hosted bundle ships the REST API and a web dashboard together.

Does Mem-zero keep persistent context out of the context window?

It stores, searches, and manages persistent context across sessions instead of filling the context window.

Answers sourced from docs.mem0.ai, forums.unraid.net, mem0.ai

Community

Collected today - public community threads