Long-term memory for AI agents. Pass one sentence, and it remembers, recalls, or forgets.
io.sepiace/sepiace — Model Context Protocol (MCP) Server
The io.sepiace/sepiace MCP server provides long-term memory for AI agents. Its described function is simple: pass one sentence, and the system can remember, recall, or forget information. The goal is to manage persistent context across agent interactions.
🛠️ Key Features
Long-term memory for AI agents
Sentence-based input to trigger remember, recall, or forget actions
🚀 Use Cases
Persisting agent context over time
Retrieving previously stored information during conversations
Removing or forgetting outdated or unwanted details
⚡ Developer Benefits
Minimal, sentence-driven interface for memory operations
Clear actions mapped to remember, recall, and forget
⚠️ Limitations
Supported behavior is limited to what is described: passing one sentence to remember, recall, or forget
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
sh
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.
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 No LLM writes or rewrites it, and when something becomes outdated, only that sentence is replaced.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.
System
Index
Remember
Replace
Forget
Tidy
sepiace
96.1
98.7
98.0
100.0
88.2
Supermemory
58.9
95.3
95.0
22.0
60.5
ByteRover
39.2
72.3
19.0
62.0
27.7
Mem0
8.5
96.3
0.0
0.0
55.0
Store everything
8.0
99.0
0.0
0.0
41.7
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
Component
What it does
MCP server
Connects https://hi.sepiace.io/api/v1/mcp. It has one tool, memory, which takes one sentence
memory skill
Tells the agent to recall before acting, to save durable facts as plain sentences about you, and never to send secrets
Session-start note
A short reminder, about 130 tokens, added when a session starts, is cleared, or is compacted
migrate skill
Moves local memories into sepiace. It runs only when you ask for it
update skill
Updates the plugin and the skills in every client to the latest version. It runs only when you ask for it
What the migrate skill reads
Source
Files
Claude Code auto memory
~/.claude/projects/*/memory/*.md
Claude Code user instructions
~/.claude/CLAUDE.md
Codex memories
~/.codex/memories/
Codex user instructions
~/.codex/AGENTS.md
It never changes the local files.
What npm create sepiace changes
Client
What it does
Claude Code, Codex
Installs the plugin from this repository
Cursor
Adds sepiace to ~/.cursor/mcp.json and the skills to ~/.cursor/skills
VS Code
Adds sepiace to the user mcp.json and the skills to ~/.copilot/skills
OpenCode
Adds sepiace to ~/.config/opencode/opencode.json and the skills to ~/.config/opencode/skills
Claude Desktop and claude.ai
Shows how to add sepiace as a custom connector
The CLI lives in cli/ and is published to npm as create-sepiace.
Install
Remote endpoint
Streamable HTTP
Hosted server - connect over the network, no local install.