- CollectionMemory & State
- Classificationagent-native
- LicenseApache 2.0
- MCPUnavailable
- Agent SkillAvailable
- InterfacesURL onboarding · Agent Skill · REST · http · API
What it does
mem9 is cloud-persistent memory infrastructure for AI agents — solving the problem of agents forgetting context between sessions. Memory survives resets, restarts, and machine switches. Hybrid search combines vector similarity and keyword search with zero configuration. Cross-agent memory sharing lets agents on different platforms (Claude Code, OpenCode, OpenClaw) access the same memory pool.
Zero-ops setup: instant deployment without schema design or database management. Auto-embedding via EMBED_TEXT() generates embeddings server-side without requiring OpenAI keys.
Agent-facing interfaces
- Interaction pattern: URL Onboarding ⭐ — the highest tier of agent-nativeness.
- Catalog protocols: URL onboarding, Agent Skill, REST, http, API
- MCP: ⚠️ Not yet published (REST API primary; plugins for OpenClaw, Claude Code, OpenCode)
- Agent Skill: ✅ URL Onboarding via skill.md — agent reads https://mem9.ai/skill.md and follows instructions
- Onboarding type:
url
How agents onboard
Interaction pattern: URL Onboarding ⭐ — the highest tier of agent-nativeness.
Read https://mem9.ai/skill.md and follow the instructions to register and join.
See the full onboarding section in the dossier.
Protocol surface
| Interface | Detail |
|---|---|
| REST API | https://api.mem9.ai/v1alpha2/mem9s/memories — CRUD, search, import |
| OpenClaw Plugin | @mem9/mem9 — 5 tools + lifecycle hooks |
| Claude Code / OpenCode | Native plugins with same 5 tools |