
Memory for AI, modeled on human memory — a local-first memory layer that turns Claude Code into a
Memory for AI, modeled on human memory — a local-first memory layer that turns Claude Code into a counterpart
·
Long-term memory for Claude Code, written by Claude itself.
Agents are great. What you're missing is a counterpart.
Each Claude Code session starts over, apart from your CLAUDE.md files and Claude's short MEMORY.md notes. With Counterparts, Claude writes down what it learned as it works and at the end of each session, in its own words. What matters sticks and the rest fades unless it comes up again. After the first few sessions, each one opens with a short note Claude wrote itself: who it is, where the work stands, what's coming up and how yesterday went, so you stop re-explaining your projects and how you like to work.
It's for anyone who works with Claude Code every day and wishes it remembered, and for people interested in an AI that builds a relationship with them over time. It runs on your machine, with Claude Code on macOS, Linux and Windows, and with Claude Desktop on macOS.
You need Node 22.15 or newer, or bun 1.3 or newer, on macOS, Linux and Windows (Windows is new: tell us how it goes). Bun on macOS is the setup in daily use; Node and Linux (since 0.3.11) pass a smoke test and an install run but have no daily user yet. On Windows, install with npm, from PowerShell, cmd or Git Bash; what differs there is in QUICKSTART. Under WSL it works as on Linux.
npm install -g counterparts@latest
counterpartsWith bun instead: bun add -g counterparts, then counterparts. Whichever runtime runs the
setup is the one Claude Code's hooks and memory tools are wired to. Or install it as a Claude
Code plugin: /plugin marketplace add mlapeter/counterparts, then
/plugin install counterparts@counterparts, then restart Claude Code. The plugin sets
itself up on its first session, with no terminal step; /counterparts:doctor checks it.
With npm or bun, the first run asks two things, and you can skip either: your name, and
whether to connect Claude Code. Connecting adds hooks to ~/.claude/settings.json (it backs
the file up first), registers the memory tools, and adds one deniedMcpServers entry there
so the hosted Counterparts Online connector never loads into Claude Code as a second memory.
Hooks and settings from other tools are left alone. No API keys and no account. Then restart
Claude Code and check it:
counterparts doctorFor Claude Desktop on macOS (since 0.3.9), run counterparts install --host claude-desktop,
then set the counterparts tools to Always allow in Claude Desktop, so a chat can wake on
its own.
The first session in a new folder asks whether you want memory there. To remove it, run
counterparts uninstall; your memory is kept unless you ask for it to be deleted. The full
walkthrough is in docs/QUICKSTART.md.
~/.counterparts, readable by your account
only. You can read, export or delete them. Search by meaning runs on a small model on your
machine, about 30 MB.password= or api_key:), and most passwords named in a sentence
("my wifi password is …", "the PIN is …"): the value goes, the sentence stays. Not every
secret has a shape, so don't paste things you wouldn't want kept.How Claude Code's own memory works, and where Counterparts fits: counterparts.ai/guides/claude-code-memory. More at counterparts.ai. A hosted version for claude.ai is coming soon, in beta; sign up on the home page to hear when it opens.
Found a bug? Open an issue. For anything else, write to [email protected].
Today's models are frozen, so memory is the only learning they do. Once a real memory works on top of a frozen model, the plan is to pair it with an open-weight model whose weights can change, so the AI can learn and grow, not just remember.
Once installed it runs on its own. A few commands are worth knowing:
counterparts dashboard # look at the memory in your browser
counterparts ask "..." # ask the memory a question
counterparts scope . --off # don't remember this directory
counterparts export --out <dir> --passphrase <secret> # an encrypted copy of everything
counterparts --help # the restExport needs --passphrase or --plaintext; it won't pick for you. No command opens an
encrypted export yet: the README written beside it gives the format (scrypt and
AES-256-GCM), so it can be opened by hand.
Memory is on for every directory by default. The first session in a new directory asks whether you want it there.
Two pieces connect it to Claude Code. Hooks load a briefing at the start of each session and bring up related memories as you talk. A small MCP server gives the AI tools to save what it learned, write a journal entry, and look things up.
The core doesn't depend on Claude Code. Each part is its own module, with a
CONTRACT.md describing what it does:
| module | what it does |
|---|---|
| store | One SQLite database, plus a rebuildable search cache and daily snapshots |
| encode | Filters what comes in: strips credentials, drops junk, scores what's new |
| remember | Takes what the AI writes during and at the end of a session |
| recall | Finds related memories as you talk |
| associate | Links memories that come up together |
| schemas | Beliefs about people and things, revised slowly |
| self | Identity, the journal, and the start-of-session briefing |
| prospective | Reminders for later, triggered by a date or a topic |
| sleep | Nightly housekeeping: fading, pruning, merging, promoting |
| physics | The math for strength and decay |
More: docs/ELI5.md (the whole system in plain words) and
docs/module-map.md.
Early. It's been the author's daily memory since September 2026, on bun and macOS; Node (22.15+) and Linux pass a smoke test and an install run but have no daily user yet. Claude Desktop has no Linux build, so on Linux it is Claude Code only. Expect rough edges, and please open an issue when you hit one.
There are no API keys, and your memory leaves your machine only through Claude Code
itself. Counterparts makes one request of its own: once a day, the background worker that
Claude Code's hooks start asks registry.npmjs.org for the newest version number, and sends
nothing about you or your memory. To stop it, set "updateCheck": false in
~/.counterparts/claude-code.json, or ask Claude to stop the update reminders.
COUNTERPARTS_UPDATE_CHECK=off or Claude Code's CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC
stops it too, set in the environment Claude Code runs in. Search by meaning runs on a small model on your machine, and a session that ends
before it's written up is written up by the next session in that project.
That small model finds close paraphrases ("my doctor" finds a note about a physician), but not a description that never names the thing: "a pet that purrs" won't find a note about your cat. Exact words are strongest, and a short memory matches better than one padded with names and details.
Counterparts is the third version of a memory project. The earlier ones (claude-engram,
engram, and bansai) were each used daily before the next was written.
CONSTITUTION.md holds the principles.
Counterparts is source-available under the Business Source License 1.1 from version 0.4.0
(see LICENSE). In short:
LICENSE is the binding text; this summary isn't. Contributions are welcome; see
CONTRIBUTING.md.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/counterparts to learn what the "Counterparts" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npm install -g counterparts@latestThis server doesn't publish a machine-readable tool manifest, and it doesn't expose a public endpoint we could ask. Connect the server locally to see what it exposes.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/counterparts)Nothing comparable is listed yet.
v0.3.54counterparts 0.3.54Release notesv0.3.53counterparts 0.3.53Release notesv0.3.52counterparts 0.3.52Release notesv0.3.50counterparts 0.3.50Release notesv0.3.49counterparts 0.3.49Release notesv0.3.48counterparts 0.3.48Release notesv0.3.47counterparts 0.3.47Release notesv0.3.46counterparts 0.3.46Release notesv0.3.45counterparts 0.3.45Release notesv0.3.44counterparts 0.3.44Release notesv0.3.43counterparts 0.3.43Release notesv0.3.42counterparts 0.3.42Release notesv0.3.41counterparts 0.3.41Release notesv0.3.40counterparts 0.3.40Release notesv0.3.39counterparts 0.3.39Release notesv0.3.38counterparts 0.3.38Release notesv0.3.37counterparts 0.3.37Release notesv0.3.36counterparts 0.3.36Release notesv0.3.35counterparts 0.3.35Release notesv0.3.34counterparts 0.3.34Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "counterparts" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.