v3 is livepersonal + code memory, one MCP endpoint

Your AI forgets.
Memo remembers.

One memory layer for every AI you use. Your preferences, facts and goals follow you into ChatGPT, Claude and Gemini — your conventions follow you into Cursor, Claude Code and Codex.

Free to start Private per account MCP for coding agents
memory-engine · claude-code
live
write

I maintain Memo, a memory layer for AI assistants and coding agents. I write TypeScript daily, expose project rules through /api/mcp, and never deploy before typecheck and tests pass.

repo: haiziyan/memo Extract
Maintains Memo, a memory layer for AI assistantsfact
Writes TypeScript and Next.js every dayskill
Serves code memory at /api/mcp with bearer tokensconvention
Runs typecheck and tests before every deploydecision
recall
How do coding agents read our rules?
Through the MCP server at /api/mcp; memory_search and memory_context return the stored code rules.
0.96
sem .84 · lex 1.0
38ms1 of 22 memorieshit
postgres · synced synced

Works with the AIs you already use

ChatGPTClaudeGeminiClaude CodeCursorCodex
~300ms
Warm recall
2
Memory layers
0
Embedding API keys
4
MCP tools
Product

Memory that behaves like a database, not a chat log.

Most agents re-read the entire transcript every turn. Memo stores the handful of things worth keeping, typed and scored, so every request starts with the right context — and you can see exactly why.

Hybrid recall

Openly licensed BGE embeddings run on the server, BM25 catches exact terms, then importance and recency re-rank. No embedding API keys, no per-token cost.

bge-small · local ONNX

Automatic extraction

Paste a conversation or upload a ChatGPT / Claude export. You get atomic memories — preferences, facts, goals, people, skills — each with a confidence score.

POST /api/import

Seven memory types

A typed store beats a wall of text. Every memory carries a category, importance, source and timestamps — so your prompts stay small.

7 categories

Every AI, one memory

Personal memory follows you into ChatGPT, Claude and Gemini as a prompt-ready context pack. Coding agents read the same store over one MCP endpoint.

MCP + context pack

Inspectable by design

Search, edit, delete and export everything. Memory should be a database your users can audit — never a black box they have to trust.

export .json

Code memory

Conventions, decisions and gotchas stored per repository. A stable key makes every save an upsert, so rules stay current instead of piling up.

owner/name · keyed upserts
How it works

Three steps from conversation to recall.

01

Bring what any AI knows

Paste a conversation or upload a ChatGPT / Claude export. Memo keeps the durable preferences, facts, goals and people, and drops the chatter.

02

Type it once

Personal memories get a category and importance. Code memories get a repository, a type and an optional key, so conventions update in place.

03

Reach every assistant

Coding agents call MCP tools on demand. Chat assistants get a prompt-ready context pack you can paste anywhere in one click.

Start with an accountno vector database required
extract.sh
# 1 — extract memories
curl -X POST https://memex-iota.vercel.app/api/extract \
  -H "Content-Type: application/json" \
  -d '{"text":"I maintain Memo. We always run typecheck and tests before deploying."}'

# 2 — response
{
  "engine": "local",
  "memories": [
    {
      "content": "Maintains Memo, a memory layer for AI assistants",
      "category": "fact",
      "importance": 0.74
    },
    {
      "content": "Runs typecheck and tests before every deploy",
      "category": "convention",
      "importance": 0.71
    }
  ]
}
POST · JSON · 200 OKworks without an API key
Extract
atomic facts
Relate
similarity edges
Score
rank + decay
The workspace

Every memory, visible and yours.

Search, filter, edit and delete from one dashboard. The graph view shows what clusters together. The playground answers questions using only what your agent actually remembers.

Open the workspace
memo.vercel.app/dashboard
console
22
Memories
7
Categories
0.74
Avg importance
2
Users
Search memories…/
Maintains Memo, a memory layer for AI assistants0.94
Serves code memory at /api/mcp with bearer tokens0.88
Runs typecheck and tests before every deploy0.81
Pricing

Start free. Scale when it works.

Simple pricing for this reference build. Start free and upgrade when your agents outgrow the free tier.

Developer
$0forever

For prototypes and side projects that still deserve real recall.

  • 5,000 memories
  • Personal + code memory
  • MCP endpoint
  • Context packs
  • JSON export
Start free
most popular
Pro
$29per month

For people who use more than one AI every day and want them to agree.

  • 100,000 memories
  • Unlimited repositories
  • Claude-backed extraction
  • Import from ChatGPT / Claude
  • Priority recall
  • Audit and export
Start free
Scale
Customtalk to us

For workloads that need regional storage, SLAs and private models.

  • Unlimited memories
  • Private deployment
  • Bring your own model
  • Custom retention
  • SSO and RBAC
  • Dedicated support
Read the docs

Give every AI
the same memory.

Create an account, then add a memory, connect a coding agent or copy a context pack. Google and GitHub sign-in are supported.