sepiace
io.sepiacePublished by sepiace.ioOfficial publisherv0.2.0Updated Oct 24, 2026
Long-term memory for AI agents. Pass one sentence, and it remembers, recalls, or forgets.
Overview
A remote long-term memory service for AI agents: the assistant passes one natural-language sentence to remember, recall, search or forget facts across sessions.
- What you can do
- Remember durable facts about the user by passing a plain sentence, such as a stated preference or decision, and have them stored per account on the server. Recall or search stored memories by asking a question in natural language, with results returned as memory text only. Forget a specific memory on request, replacing outdated facts with the newer sentence. Optionally migrate existing local memories from Claude Code and Codex into the service, and update the plugin and skills across clients.
- When to use it
- Useful when you want an assistant to carry preferences, decisions and other durable facts between sessions without re-explaining them, and you are comfortable storing those memories on a hosted service tied to an account.
- Requirements
- A remote Streamable HTTP endpoint at hi.sepiace.io, added as a remote MCP server; sign-in is through OAuth in the browser. The optional setup helper is run via npm and can configure Claude Code, Codex, Cursor, VS Code and OpenCode. No environment variables or headers are declared.
Installation
In SourceWeft
- Open sepiace in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.sepiace%2Fsepiace/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"sepiace": {
"type": "http",
"url": "https://hi.sepiace.io/api/v1/mcp"
}
}
}README
sepiace
Long-term memory for AI agents. Your agent passes one natural-language sentence, and sepiace remembers, recalls, or forgets.
[Star sepiace on GitHub]
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
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:
Codex:
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.
KiokuBench v0.1, 10 personas in English and Japanese, raw conversation passed in as is. sepiace was measured on October 14, 2026, and the others between September 27 and 30, 2026. KiokuBench was designed and run by the team that builds sepiace. The method, the eight metrics, the conditions for each system, and the limitations are on sepiace.io.
Specification
Plugin components
What the migrate skill reads
It never changes the local files.
Source: README.md at commit 34b3dc6
Tools
0Version history
1- v0.2.0LatestOct 15, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts