# mem9-ai/mem9

Unlimited memory for OpenClaw

Repository: https://github.com/mem9-ai/mem9
Canonical: https://ross.abutalabs.com/products/mem9
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: dsh-plugin
Last push: 2026-08-25T07:46:23+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 12
- inputs: {"age_days": 178, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1201, forks 122 (observed 2026-08-28T04:03:58.280185+00:00)

## What it is
mem9 is a persistent memory layer for AI agents, providing cross-session and cross-machine memory, shared memory for multi-agent workflows, and hybrid recall with a visual dashboard. It offers a hosted API and a self-hostable Go server backed by TiDB, with plugins for OpenClaw, Claude Code, OpenCode, Codex, and other agent runtimes.

## Use cases
- give my ai agent persistent memory across sessions
- share memory between multiple ai agents
- remember context between coding agent sessions
- self-host a memory server for llm agents
- add long-term memory to claude code or openclaw
- agent forgets everything between conversations

## When to choose
- you run AI coding agents that lose context between sessions
- you need shared memory across multiple agents or machines
- you want a choice between hosted API and self-hosted deployment

## When to avoid
- you need simple in-process memory for a single-session app
- you want a fully offline memory store with no server component
- your stack has no HTTP client or supported plugin integration

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, rag, vector-database, api-framework, mcp
- domain: large-language-models, developer-tools, self-hosted
- platform: self-hosted, cloud, go
- tags: persistent-memory, ai-agent-memory, multi-agent, openclaw, claude-code, hybrid-recall, memory-layer, ai-agents, nodejs, docker

## Member repositories
- mem9-ai/mem9 (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:58.280185+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:20:42.832870+00:00, confidence not recorded.
  - readme: https://github.com/mem9-ai/mem9 (fetched 2026-08-28T04:03:58.280185+00:00, sha 41c2c57e3497)
- Data as of 2026-08-30T08:39:29.467469+00:00.