Corvid
About
Free, no-signup persistent memory for AI agents over MCP — remember/recall facts across sessions with one hosted URL. Zero setup, no API key.
Details
- Author
- Unknown
- Categories
- AI
Jump to
Give your AI a memory that survives the session.
Corvid is a free, no-signup memory store your AI assistant can read and write overMCP— or any agent can hit over a plain HTTP API. Create a space, drop one URL into your client config, and your agent starts torememberandrecall. Recall issemantic— it finds notes by meaning, so a question about "deployment" surfaces a memory that says "ships on Cloudflare Workers." No account, no API keys, no SDK.
One click. You get a private space + token. Nothing to sign up for.
2. Try it live — right here in your browser
See the round trip your agent makes. Store a memory, then search for it — this hits the real API against your own private space.
Why CorvidNo signupMCP-nativeSemantic recallPlain HTTP too4 tools: remember / recall / list / forgetFree
Most memory tools want an account, an API key, and a client library. Corvid is the opposite: a single MCP URL (with your token) is the whole integration. Point Claude Desktop, Cursor, or your own agent at it and memory Just Works — across chats, across days.
- Your assistant callsremember("Ada prefers TypeScript and 2-space indent")when you tell it something worth keeping.
- Next session it callsrecall("Ada's code style")and gets it back — no re-explaining.
- Everything lives in your space, keyed to your token. Delete any memory withforget.
Read the docsSet up with Claude / Cursor
Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.
Persistent memory and semantic search for AI coding assistants across sessions
Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.
Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.
Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.
Your portable AI memory vault — memories, skills & configs, shared across every AI tool.
Local Work Model for AI agents that learns from real outcomes.
Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
