Shared long-term memory for AI coding agents

Your whole team's memory, in every agent.

Every teammate's Claude Code session pours what it learns into one shared memory — rules, architecture, commands, hard-won lessons — reviewed by a human and handed to the next agent, for anyone on the team, before it touches a file.

1,843 engineers already in line
  • ✦ Learned once, shared by all
  • ✓ Reviewed before agents see it
  • ◆ Works with Claude Code, Codex, Cursor
memmo · team memorylive
MALEPRSAAD
Maya · claude code
session #341 · ephemeral
→ shared memory✦
team memory · shared1,247 retained
  • riskbilling-apivia Maya

    Duplicate-invoice outage in March — always set an idempotency key on refunds.

  • decisionbilling-apivia Ade

    Stripe webhooks are the source of truth — reconcile, don't trust the client.

  • conventionapivia Sam

    All money is stored in integer cents — never floats, anywhere.

  • riskwebvia Priya

    Don't bump Prisma to v6 — it breaks the migration runner in CI.

one teammate learns it once — every agent on the team inherits it

Today

Every session starts from zero.

You explain the same conventions again. The agent re-discovers the same landmine. The fix you argued about last week gets undone. Nothing it learns survives the session.

With Memmo

Every session makes the next one smarter.

What your team learns while working becomes short, reviewed memories — and every future session, for every teammate, starts already knowing them.

How it works

Capture. Review. Inject.

Three steps, running quietly in the background of the work you already do.

  1. 01

    Capture

    Memory comes from real work, not from writing docs.

    When a Claude Code session ends, Memmo reads what happened — the corrections you gave, the decisions the agent made, the commands that failed — and proposes short, atomic memories. Merged PRs and a one-time repo scan propose more.

  2. 02

    Review

    A human approves. Nothing reaches an agent unreviewed.

    Proposals land in an inbox. Approve, edit, reject — or set confidence thresholds and let obvious ones through. Corrections supersede the memory they replace, so knowledge evolves instead of piling up.

  3. 03

    Inject

    Every session starts already knowing.

    At session start the agent gets a briefing: rules, architecture, key commands, known risks. When you type a task, the memories relevant to it are pulled in. Before it edits a risky file, it's warned.

What the agent sees at session start

claude code · session start · acme/billing-api
Memmo — what this team already knows about this repo:

Project rules & decisions:
- Run lint before every push — CI rejects unformatted code.
- Cache reads only — writes stay uncached (cart consistency).

Architecture:
- Billing is event-driven off Stripe webhooks → invoice-worker.

Key commands:
- Use make test-billing — the full suite times out on billing.

Known risks — check before touching related code:
- Stripe webhooks must be idempotent — a missing key caused the
  March duplicate-invoice outage.

What a memory is

One fact. Short enough to act on.

Not a wiki page. Each memory is one rule, risk, command or decision — a sentence or two, typed, scoped to the repos it applies to, optionally pinned to file paths.

  • ✓Atomic — one thing per memory, so it can be approved, corrected or retired on its own.
  • ✓Typed — rule · architecture · command · decision · risk · failure · workflow …
  • ✓Scoped — to the whole project or to specific repos; risks can carry file globs.
  • ✓Traceable — each carries its evidence, its source session and its usage count.
project ruleAll repos

Run lint before every push

Every repo in this project must run `pnpm lint` before pushing — CI rejects unformatted code.

riskacme/billing-apisrc/billing/webhooks/**

Stripe webhooks must be idempotent

A duplicate-invoice outage came from a webhook without an idempotency key. Check keys before touching handlers.

commandacme/billing-api

Use the targeted billing tests

The full suite times out on billing. Run `make test-billing` instead.

decisionacme/checkout

Cache reads only, never writes

GET responses are cached at the edge; writes stay uncached because carts must be consistent across devices.

Get started

Connected in under a minute. No config files.

The git remote is the identity. memmo init registers the repo, wires Claude Code, and offers a scan that proposes starter memories. Teammates who clone the repo just sign in.

  • ✓ Nothing to maintain — just .mcp.json, CLAUDE.md and hooks, committed once
  • ✓ Runs on your Claude Code subscription — no API key needed to start
  • ✓ Other agents connect over hosted MCP with one command
Full setup guide →
your-repo — setup
$ npm install -g @memmo/cli
$ memmo login
$ memmo init

Connected acme/billing-api → project "Acme".
  - created .mcp.json
  - created CLAUDE.md
  - registered 4 Memmo hook(s) in .claude/settings.json

Scan this repo now to propose starter memories? (Y/n) y
Deep scan complete in 94s — 23 new memory proposal(s) waiting in your Inbox.
get_repo_contextsearch_memoryget_relevant_warningspropose_memories

Built for teams

Small team or forty repos — the same four screens.

Memory, Inbox, Connect, Settings. That's the whole app.

Projects, not silos

A project is the set of repos that share one memory — one monorepo, or twenty services. A memory applies to all of them or to specific repos.

Search by meaning

“What breaks when I touch webhooks?” finds the idempotency incident. Semantic search runs locally — no vector database, no extra keys.

Memory that evolves

When the facts change, a correction supersedes the old memory on approval. Duplicates are caught before they reach the inbox.

Just-in-time warnings

Attach file globs to a risk and the agent is warned the moment it goes to edit a matching file — not buried in a doc it never read.

Works with any agent

Claude Code gets the full loop (hooks + MCP). Codex, Cursor and Claude Desktop read the same memory over hosted MCP.

Your keys, your audit trail

Bring your own Anthropic, OpenAI or Google key for extraction. Every approve, edit and supersede is logged.

Start free. Pay for usage, not seats.

Invite your whole team on every plan — you're only metered on how often your agents pull memory.

Free

$0forever · no card

For solo devs and small teams getting started.

Get started free
  • ✓1 project
  • ✓Unlimited teammates
  • ✓1,000 memory retrievals / month
  • ✓Inbox, briefing, warnings, semantic search
Most popular

Scale

Usage-basedunlimited seats

For teams that rely on it every day.

Start free, upgrade in-app
  • ✓Everything in Free
  • ✓Unlimited projects
  • ✓50,000 retrievals / month
  • ✓Memory-grounded PR reviewer
  • ✓Audit log

Enterprise

Customtalk to us

For regulated teams that need control.

Talk to us
  • ✓Everything in Scale
  • ✓Unlimited retrievals
  • ✓Self-host in your own VPC
  • ✓SSO & priority support
  • ✓SLA

Make every AI coding session compound.

Give your agents a memory that grows with your team — starting with the next session.

1,843 engineers already in line