Tired of copying a chat into the next agent? Pick up the same task where you left off, or tell one agent to put the others to work.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/rxthlessbeats/agent-cowork-memory && cp agent-cowork-memory/*.md ~/.claude/agents/Subagents overview
# Agent Cowork Memory (ACM) Tired of copying a chat into the next agent? Pick up the same task where you left off, or tell one agent to put the others to work. [Demo](https://acm-website-sand.vercel.app/)          Codex ·  Claude Code ·  Cursor ·  OpenCode ## Demo [ACM official site](https://acm-website-sand.vercel.app/) ## Install With [Node 24](https://nodejs.org) or newer: ```sh npx -y agent-cowork-memory setup ``` Setup adds ACM to Cursor, and to Codex, Claude Code, and OpenCode when they are installed; it says which it skipped. Installed one later? Run setup again. Restart your agents, and ACM is available in every project. Each agent starts ACM through npx, which runs the latest release whenever the npm registry answers within 3 seconds, so there is nothing to update. Coming from 0.2? 0.3 starts a fresh database (`~/.agent-cowork-memory/acm.sqlite3`); 0.2's notes stay in `state.sqlite3`, untouched, and are not carried over. Tested for real on Linux and WSL. macOS and Windows pass CI; real runs welcome. ## Use ### Memory Sharing Open the same project in Codex and Cursor. To pick up a chat in the other agent, ask: > Use ACM to continue from Cursor. Or, in Cursor: > Use ACM to continue from Codex. Every agent can see every chat in the project. If there is more than one, the agent lists them (agent, time, thread, first message, and whether ACM started it for a delegated job) and asks you which one to continue. You can also name it: > Use ACM to continue the Codex chat about the trip. Related work goes together in a **thread**: continuing a chat, or delegating from it, keeps the work on one thread, and a new chat can join one of the project's open threads. ACM keeps each thread's timeline as things happen (chats joining, jobs starting and finishing, notes added), so any agent can see where the work stands. Ask your agent to remember a decision, and every agent in the project sees it. Notes stay true: when a new note may contradict an old one, the agent is shown the old one and replaces it if it's wrong, and when a file a note mentions changes, the note is marked to re-check. ### Delegate to other agents Any agent can hand work to the others: > Tell codex to write plan.md, and claude to write packing.md. Each agent gets a brief, joins the thread it was sent from, claims the files it edits so they don't collide, and reports back. Agents run in the background. With [herdr](https://herdr.dev) installed, each one gets its own pane you can watch (`herdr session attach acm`). Delegated agents run in each agent's auto mode: Codex `--approve-for-me`, Claude Code `--permission-mode auto`, and Cursor `--auto-review` (with `--trust --approve-mcps`, so it opens the project and ACM without asking). Safe actions run on their own. When auto mode denies an action, the agent stops, and ACM reports the job as `needs_approval` to the chat that delegated it. A background job still running after 15 minutes is stopped and reported the same way. Approve it there, and that agent runs the step or delegates again. If an agent asks a question in its herdr pane instead, ACM reports the job as `blocked` until you answer it there. ## MCP tools | Tool | What it does | | --------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `context` | Your thread and its timeline, the project's notes (after the first call, only what's new), open threads, recent jobs, who is working, and held files. Pass `hold` to claim files before writing, `thread` to join one, `done` to close yours. `stale` lists notes whose files changed, to re-check. | | `note_add` | Saves a note every agent sees, and shows notes it may contradict. `tier`: `short` (default, kept 7 days) or `long`; `supersedes`: the note it replaces. | | `note_search` | Finds notes and delegated jobs' results. | | `chats` | Lists recent chats from every agent in the project, and marks the ones ACM started. | | `resume` | Asks you which chat to continue when there are several, then reads it and joins its thread. | | `delegate` | Starts other agents with a brief, in herdr panes or in the background, and waits for them. | | `delegate_wait` | Keeps waiting on this chat's delegated agents. | ACM tells which chat it is in on its own; no tool needs a session or, from the project folder, a path (every tool takes an optional `repo_path`). ## CLI | Command | What it does | | ------------------------------------------------------------- | ---------------------------------------------------------------------------- | | `acm setup` | Adds ACM to your agents. | | `acm mcp --harness <agent>` | Runs the MCP server; agents start it themselves. | | `acm status [--repo <dir>] [--chat <id>] [--harness <agent>]` | The project's jobs, held files, and a chat's thread, as JSON. | | `acm doctor` | Checks the install: Node, the database, herdr, and which agents are on PATH. | | `acm backup [--to <file>]` | Copies the database. | `--home <dir>` (or `ACM_HOME`) moves ACM's state folder from `~/.agent-cowork-memory`. Run them with `npx -y agent-cowork-memory <command>`, or `acm` once it's installed globally.
What people ask about agent-cowork-memory
What is rxthlessbeats/agent-cowork-memory?
+
rxthlessbeats/agent-cowork-memory is subagents for the Claude AI ecosystem. Tired of copying a chat into the next agent? Pick up the same task where you left off, or tell one agent to put the others to work. It has 0 GitHub stars and its last recorded update is dated 2026-10-06.
How do I install agent-cowork-memory?
+
You can install agent-cowork-memory by cloning the repository (https://github.com/rxthlessbeats/agent-cowork-memory) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is rxthlessbeats/agent-cowork-memory safe to use?
+
Our security agent has analyzed rxthlessbeats/agent-cowork-memory and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains rxthlessbeats/agent-cowork-memory?
+
rxthlessbeats/agent-cowork-memory is maintained by rxthlessbeats. The last recorded GitHub activity is dated 2026-10-06, with 0 open issues.
Are there alternatives to agent-cowork-memory?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy agent-cowork-memory to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/rxthlessbeats-agent-cowork-memory)<a href="https://claudewave.com/repo/rxthlessbeats-agent-cowork-memory"><img src="https://claudewave.com/api/badge/rxthlessbeats-agent-cowork-memory" alt="Featured on ClaudeWave: rxthlessbeats/agent-cowork-memory" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
The agent engineering platform.