Supermemory
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era. observed · 2026-08-28
Health v2 · maintenance only
92/100
- Activity 99
- Release rhythm 98
- Longevity 65
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 2
- age_days: 918
- days_rel: 16
- days_push: 7
- n_releases_24m: 8
Adoption not part of the score
29089 stars · 2529 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Supermemory is a memory and context engine for AI applications and agents, offering a hosted Memory API plus a self-hostable stack that extracts facts from conversations, maintains user profiles, and provides hybrid RAG search. It ships with MCP servers, editor/agent plugins, connectors (Gmail, Notion, Google Drive, GitHub), and a team-facing 'Company Brain' agent.
Use cases
- give my ai chatbot long-term memory across sessions
- add persistent memory to my coding agent
- build a rag pipeline over my documents and chats
- share team knowledge with claude or cursor via mcp
- auto-build user profiles from conversations for personalization
- self-host a memory engine for my ai agents
- sync notion and google drive into an ai knowledge base
When to choose
- you need state-of-the-art agent memory with benchmarks backing it (LongMemEval, LoCoMo)
- you want a managed memory API with SDKs for TypeScript and Python
- you want MCP integration so multiple AI assistants share one memory layer
- you need both RAG retrieval and conversational memory in one system
- you want to self-host the full stack on Cloudflare Workers
When to avoid
- you only need a plain vector database without memory extraction or profiles
- you need a fully offline solution with no cloud dependency and can't run the self-hosted stack
- your stack has no JavaScript/Python SDK support and you can't call REST APIs
- you want a simple key-value store rather than semantic memory infrastructure
Facets
service · maturity active
rag vector-database search-engine mcp agent-framework chatbot sdk webhook api-framework artificial-intelligence large-language-models chatbots developer-tools self-hosted cloud self-hosted python serverless ai-memory agent-memory memory-api context-engine user-profiles connectors company-brain long-term-memory mcp-server cloudflare-workers ai-agents retrieval-augmented-generation web-server nodejs docker
8 sources
- readme: https://github.com/supermemoryai/supermemory · fetched 2026-08-28 · 9c135c6b600f
- homepage: https://supermemory.ai/docs · fetched 2026-08-29 · c9e3e9b86fd6
- site_page: https://supermemory.ai/docs/overview/what-is-supermemory · fetched 2026-08-29 · 05bb05def898
- site_page: https://supermemory.ai/docs/supermemory-mcp/mcp · fetched 2026-08-29 · aa62d0a52dd2
- site_page: https://supermemory.ai/docs/company-brain/overview · fetched 2026-08-29 · 37f161ff588f
- site_page: https://supermemory.ai/quickstart · fetched 2026-08-29 · 472b0b63f633
- registry_npm: https://registry.npmjs.org/opencode-supermemory · fetched 2026-08-29 · 417ea18770e4
- site_page: https://supermemory.ai/changelog · fetched 2026-08-29 · 03d5e9d93c7a
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| supermemoryai/supermemory | main | 92 |
| supermemoryai/claude-supermemory | plugin | 60 |
| supermemoryai/supermemory-mcp | plugin | 45 |
| supermemoryai/opencode-supermemory | plugin | 60 |
For agents
markdown · JSON · MCP: product_card(name="supermemoryai/supermemory")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem