Supermemory
Memory and context engine for agents with an API, app and MCP server, which can also run fully locally.
Updated
✨ Try AgentScout's free AI image generator →Good for: connecting tools with MCP, memory for agents, running agents locally
Use cases
About Supermemory
Supermemory is listed in our memory & RAG category and is aimed at builders. Memory and context engine for agents with an API, app and MCP server, which can also run fully locally. Pricing, as the maker states it: Open source + cloud. Maturity: Mature. We last checked the official link on 2026-10-18.
What is Supermemory?
Supermemory is a memory and context engine for AI. It learns from conversations, extracts facts, builds user profiles, handles updates and contradictions, and forgets expired information, so an AI keeps context between conversations.
It combines memory with full RAG, connectors (Google Drive, Gmail, Notion, OneDrive and GitHub) and extractors for PDFs, images, video and code. It can give coding tools such as Claude Code, Cursor, Codex and OpenCode persistent memory, and can be self-hosted.
Sources: the official README and our directory listing, checked 2026-10-18. Official site: supermemory.ai.
Who is Supermemory for?
Developers adding long-term memory and personalization to AI apps or agents, and people who want their coding assistants to remember past work.
Supermemory at a glance
- Open source: Yes (MIT License)
- GitHub: supermemoryai/supermemory · 31,341 stars (as of Oct 21, 2026)
Key features
- Fact extraction with handling of updates and contradictions
- Auto-maintained user profiles
- Hybrid search across memory and documents
- Connectors for Google Drive, Gmail, Notion, OneDrive and GitHub
- PDF, image, video and code extractors
- Plugins for Claude Code, Cursor, Codex and OpenCode; self-hostable
Supermemory FAQ
What is Supermemory?
Supermemory is a memory and context engine for AI. It learns from conversations, extracts facts, builds user profiles, handles updates and contradictions, and forgets expired information, so an AI keeps context between conversations.
Who is Supermemory for?
Developers adding long-term memory and personalization to AI apps or agents, and people who want their coding assistants to remember past work.
Is Supermemory free?
Supermemory's pricing, as the maker states it: Open source + cloud. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Is Supermemory open source?
Yes. Supermemory is released under the MIT License, according to its GitHub repository.
What are alternatives to Supermemory?
Similar tools include Zep, Claude-Mem, MemPalace, LongMemory, OpenViking and MarkItDown.
Supermemory ratings and reviews
Be the first to rate Supermemory: tap 1 to 5 stars below. A written review is optional.
Supermemory alternatives
Other memory & RAG tools in our directory. See all memory & RAG tools →
Zep
Context layer that unifies business data, documents and conversations into memory so agents complete tasks correctly.
Claude-Mem
Gives coding agents memory across sessions by capturing what they do, compressing it and feeding the relevant context back in later.
MemPalace
Local-first AI memory system that stores conversations verbatim with a pluggable backend and serves recall to agents without API calls.
LongMemory
Local-first memory engine for agents that keeps durable, time-aware memories in SQLite and serves them to Claude, Copilot, Codex and others over MCP, CLI or HTTP.
OpenViking
Context database for AI agents that keeps memory, knowledge and skills in one inspectable virtual filesystem agents can navigate.
MarkItDown
Microsoft's Python tool and MCP server that converts PDFs, Office documents, images, audio and web pages to Markdown for LLM and agent pipelines.
Related lists
🏆 Ranked in: MarkItDown alternatives · Hindsight alternatives
🔁 Listed in: MemPalace alternatives · MarkItDown alternatives · Hindsight alternatives
🧭 Task guides: Local and self-hosted tools for agent memory
Badge for makers
Built Supermemory? Add this badge to your README or site. It links back to this page. About badges
