sepiace MCP server

sepiace

Long-term memory for AI agents. Your agent passes one natural-language sentence, and sepiace remembers, recalls, or forgets.

If sepiace helps you, a star keeps us going.

[!IMPORTANT]

sepiace is in beta. Memories are stored on the sepiace server at hi.sepiace.io, separately for each account. Do not ask your agent to remember passwords, API keys, or other secrets.

Quick start

npm create sepiace

It finds Claude Code, Codex, Cursor, VS Code, and OpenCode on your machine, connects the ones you choose, and walks you through signing in. Then start a new session and ask your agent:

• "Remember that I prefer pnpm over npm."
• "What did we decide about the release schedule?"
• "Forget my old home address."

To bring over what your agent already remembers, run /sepiace:migrate in Claude Code, or ask other clients to use the sepiace-migrate skill. It shows you what it found and sends nothing until you agree.

Install by hand

Claude Code:

/plugin marketplace add osaxyz/sepiace
/plugin install sepiace@sepiace

Codex:

codex plugin marketplace add osaxyz/sepiace
codex plugin add sepiace@sepiace
codex mcp login sepiace

Other MCP clients: add https://hi.sepiace.io/api/v1/mcp as a remote MCP server (Streamable HTTP). The client signs in through OAuth in the browser.

Technology

One sentence in, memory text out

Your agent writes what it wants in plain words. A judgment network on the server decides whether to save, recall, search, or forget, and combines them when needed. The response contains only memory text, with no IDs, dates, or scores, so the agent spends no tokens building structured arguments.

Memories are your own words

Each memory is cut from the sentences in the request. No LLM writes or rewrites it, and when something becomes outdated, only that sentence is replaced. A memory stays in the language you wrote it in.

Memories fade unless they are used

Each memory's score follows the FSRS forgetting curve and is computed when it is read. Memories that go unused fade, and once a memory's recall probability drops below 50%, it no longer appears in search. Each recall makes it stick.

Your memories stay yours, and you can see every request

Memories are kept separately for each account, and every database query and vector search is scoped to the signed-in user. The console at hi.sepiace.io lists every request with the memories it changed, and a client you disconnect there stops working right away.

Measured with KiokuBench

KiokuBench checks what a memory system actually stored: whether it kept the facts, replaced outdated ones, forgot what it was asked to forget, and stayed tidy. The KiokuBench Index combines these four pillars into one number from 0 to 100.

Shortened. The full README is on GitHub.