fb76b5eeef
Three coordinated fixes after phases 12, 13, 14, 15 all landed in
parallel on nexus/design-system-migration:
1. TopStrip.test.tsx provider stubs for phase 14 contexts.
Phase 14 wired CmdKButton to a new CommandPaletteContext via the
useCommandPalette() hook. TopStrip renders CmdKButton internally,
so its existing tests (written in phase 8 before the context
existed) throw "useCommandPalette must be used within a
CommandPaletteProvider" on every case. Same issue on GlobalMicButton
which now reads from VoiceContext.
Fix: add module-scope vi.mock() stubs for both contexts returning
minimal shapes, matching the existing CompanyContext mock pattern
already in the file. No test semantics change - the TopStrip is
still rendered in isolation, still verified to contain the three
children (ModeBreadcrumb, CmdKButton, GlobalMicButton) and the
header landmark. All 4 TopStrip tests pass again.
Phase 15's report flagged this breakage explicitly and confirmed
via git stash that it was pre-existing on phase 14's HEAD, not
introduced by phase 15.
2. PromoteTransition mobile variant.
Phase 15 deferred the mobile variant of the promote-to-project
transition because PromoteTransition.tsx did not yet exist when
phase 15 started (phase 12 created it mid-dispatch). The defer
was correct per explicit instructions.
Fix: add a CSS media query inside the existing scoped <style>
block in PromoteTransition.tsx:
@media (max-width: 767px) {
.nx-promote-ribbon[data-pstate="prompting"],
.nx-promote-ribbon[data-pstate="creating"] {
max-height: 0;
box-shadow: none;
overflow: hidden;
}
.nx-promote-label[data-pstate="prompting"],
.nx-promote-label[data-pstate="creating"] {
display: none;
}
}
On mobile the brainstormer completely covers the chat thread
instead of sharing a 30/70 split, per spec section 9.1. The panel
itself already takes the remaining viewport height via flex, so
once the ribbon collapses to zero the brainstormer naturally
fills the whole area.
Pure CSS - no JS media query, no useMediaQuery call, no test
changes needed. Single 768px breakpoint matches the rest of the
Nexus frame.
3. Layout.tsx onSearch now calls useCommandPalette().setOpen(true)
directly instead of dispatching a synthetic Cmd+K keydown.
Phase 14 installed a real command palette context with a provider
mounted in main.tsx, but left Layout.tsx's onSearch callback using
the old synthetic keydown shim because Layout is phase 15-owned
(parallel dispatch rules). The synthetic dispatch worked end-to-end
because the provider's global keydown listener catches it, but it's
a code smell: a Layout-level callback generating a synthetic event
for a listener the Layout also owns.
Fix: import useCommandPalette, hold a commandPalette ref in the
Layout body, and replace the synthetic keydown dispatch with
commandPalette.setOpen(true). Drop the Phase 8 shim comment; leave
a single-line Phase 14 explanation.
All 294 tests pass across 37 test files (frame, assistant, studio,
projects, settings, Voice/CommandPalette contexts, home-status and
gate-indicator and promote-to-project hooks, StudioWorkshopDetail
page). Typecheck clean across every wave 1-3A file plus App.tsx
and Layout.tsx.
Known deferrals not addressed in this commit:
- MobileTabBar does not port MobileBottomNav's "new issue" FAB or
inbox badge count. Spec section 9.1 says 4 destinations only;
requires user decision on whether to restore as a separate mobile
affordance or route through the command palette.
- VoiceMicButton.tsx and useVadRecorder.ts are now dead code after
phase 14's ChatInput migration. Both are in the phase 16 cleanup
plan's deletion list.
- Destination regexes are duplicated between IconRail and
MobileTabBar. Phase 16 DRY target via a shared frame/destinations
module.
- Phase 13 left ui/src/lib/instance-settings.ts whitelisting
/heartbeats and /experimental paths. Redirect routes catch these,
so the whitelist is cosmetic; phase 16 cleanup target.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .agents/skills | ||
| .claude/skills | ||
| .github | ||
| .planning | ||
| cli | ||
| doc | ||
| docker | ||
| docs | ||
| evals | ||
| packages | ||
| patches | ||
| releases | ||
| report | ||
| scripts | ||
| server | ||
| skills | ||
| tests | ||
| ui | ||
| .dockerignore | ||
| .env.example | ||
| .gitignore | ||
| .mailmap | ||
| .npmrc | ||
| AGENTS.md | ||
| CONTRIBUTING.md | ||
| ctl.sh | ||
| Dockerfile | ||
| LICENSE | ||
| MIGRATION-PLAN.md | ||
| package.json | ||
| pnpm-lock.yaml | ||
| pnpm-workspace.yaml | ||
| README.md | ||
| tsconfig.base.json | ||
| tsconfig.json | ||
| vitest.config.ts | ||
Quickstart · Docs · GitHub · Discord
What is Paperclip?
Open-source orchestration for zero-human companies
If OpenClaw is an employee, Paperclip is the company
Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Bring your own agents, assign goals, and track your agents' work and costs from one dashboard.
It looks like a task manager — but under the hood it has org charts, budgets, governance, goal alignment, and agent coordination.
Manage business goals, not pull requests.
| Step | Example | |
|---|---|---|
| 01 | Define the goal | "Build the #1 AI note-taking app to $1M MRR." |
| 02 | Hire the team | CEO, CTO, engineers, designers, marketers — any bot, any provider. |
| 03 | Approve and run | Review strategy. Set budgets. Hit go. Monitor from the dashboard. |
COMING SOON: Clipmart — Download and run entire companies with one click. Browse pre-built company templates — full org structures, agent configs, and skills — and import them into your Paperclip instance in seconds.
| Works with |
 OpenClaw |
 Claude Code |
 Codex |
 Cursor |
 Bash |
 HTTP |
If it can receive a heartbeat, it's hired.
Paperclip is right for you if
- ✅ You want to build autonomous AI companies
- ✅ You coordinate many different agents (OpenClaw, Codex, Claude, Cursor) toward a common goal
- ✅ You have 20 simultaneous Claude Code terminals open and lose track of what everyone is doing
- ✅ You want agents running autonomously 24/7, but still want to audit work and chime in when needed
- ✅ You want to monitor costs and enforce budgets
- ✅ You want a process for managing agents that feels like using a task manager
- ✅ You want to manage your autonomous businesses from your phone
Features
🔌 Bring Your Own AgentAny agent, any runtime, one org chart. If it can receive a heartbeat, it's hired. |
🎯 Goal AlignmentEvery task traces back to the company mission. Agents know what to do and why. |
💓 HeartbeatsAgents wake on a schedule, check work, and act. Delegation flows up and down the org chart. |
💰 Cost ControlMonthly budgets per agent. When they hit the limit, they stop. No runaway costs. |
🏢 Multi-CompanyOne deployment, many companies. Complete data isolation. One control plane for your portfolio. |
🎫 Ticket SystemEvery conversation traced. Every decision explained. Full tool-call tracing and immutable audit log. |
🛡️ GovernanceYou're the board. Approve hires, override strategy, pause or terminate any agent — at any time. |
📊 Org ChartHierarchies, roles, reporting lines. Your agents have a boss, a title, and a job description. |
📱 Mobile ReadyMonitor and manage your autonomous businesses from anywhere. |
Problems Paperclip solves
| Without Paperclip | With Paperclip |
|---|---|
| ❌ You have 20 Claude Code tabs open and can't track which one does what. On reboot you lose everything. | ✅ Tasks are ticket-based, conversations are threaded, sessions persist across reboots. |
| ❌ You manually gather context from several places to remind your bot what you're actually doing. | ✅ Context flows from the task up through the project and company goals — your agent always knows what to do and why. |
| ❌ Folders of agent configs are disorganized and you're re-inventing task management, communication, and coordination between agents. | ✅ Paperclip gives you org charts, ticketing, delegation, and governance out of the box — so you run a company, not a pile of scripts. |
| ❌ Runaway loops waste hundreds of dollars of tokens and max your quota before you even know what happened. | ✅ Cost tracking surfaces token budgets and throttles agents when they're out. Management prioritizes with budgets. |
| ❌ You have recurring jobs (customer support, social, reports) and have to remember to manually kick them off. | ✅ Heartbeats handle regular work on a schedule. Management supervises. |
| ❌ You have an idea, you have to find your repo, fire up Claude Code, keep a tab open, and babysit it. | ✅ Add a task in Paperclip. Your coding agent works on it until it's done. Management reviews their work. |
Why Paperclip is special
Paperclip handles the hard orchestration details correctly.
| Atomic execution. | Task checkout and budget enforcement are atomic, so no double-work and no runaway spend. |
| Persistent agent state. | Agents resume the same task context across heartbeats instead of restarting from scratch. |
| Runtime skill injection. | Agents can learn Paperclip workflows and project context at runtime, without retraining. |
| Governance with rollback. | Approval gates are enforced, config changes are revisioned, and bad changes can be rolled back safely. |
| Goal-aware execution. | Tasks carry full goal ancestry so agents consistently see the "why," not just a title. |
| Portable company templates. | Export/import orgs, agents, and skills with secret scrubbing and collision handling. |
| True multi-company isolation. | Every entity is company-scoped, so one deployment can run many companies with separate data and audit trails. |
What Paperclip is not
| Not a chatbot. | Agents have jobs, not chat windows. |
| Not an agent framework. | We don't tell you how to build agents. We tell you how to run a company made of them. |
| Not a workflow builder. | No drag-and-drop pipelines. Paperclip models companies — with org charts, goals, budgets, and governance. |
| Not a prompt manager. | Agents bring their own prompts, models, and runtimes. Paperclip manages the organization they work in. |
| Not a single-agent tool. | This is for teams. If you have one agent, you probably don't need Paperclip. If you have twenty — you definitely do. |
| Not a code review tool. | Paperclip orchestrates work, not pull requests. Bring your own review process. |
Quickstart
Open source. Self-hosted. No Paperclip account required.
npx paperclipai onboard --yes
If you already have Paperclip configured, rerunning onboard keeps the existing config in place. Use paperclipai configure to edit settings.
Or manually:
git clone https://github.com/paperclipai/paperclip.git
cd paperclip
pnpm install
pnpm dev
This starts the API server at http://localhost:3100. An embedded PostgreSQL database is created automatically — no setup required.
Requirements: Node.js 20+, pnpm 9.15+
FAQ
What does a typical setup look like? Locally, a single Node.js process manages an embedded Postgres and local file storage. For production, point it at your own Postgres and deploy however you like. Configure projects, agents, and goals — the agents take care of the rest.
If you're a solo-entreprenuer you can use Tailscale to access Paperclip on the go. Then later you can deploy to e.g. Vercel when you need it.
Can I run multiple companies? Yes. A single deployment can run an unlimited number of companies with complete data isolation.
How is Paperclip different from agents like OpenClaw or Claude Code? Paperclip uses those agents. It orchestrates them into a company — with org charts, budgets, goals, governance, and accountability.
Why should I use Paperclip instead of just pointing my OpenClaw to Asana or Trello? Agent orchestration has subtleties in how you coordinate who has work checked out, how to maintain sessions, monitoring costs, establishing governance - Paperclip does this for you.
(Bring-your-own-ticket-system is on the Roadmap)
Do agents run continuously? By default, agents run on scheduled heartbeats and event-based triggers (task assignment, @-mentions). You can also hook in continuous agents like OpenClaw. You bring your agent and Paperclip coordinates.
Development
pnpm dev # Full dev (API + UI, watch mode)
pnpm dev:once # Full dev without file watching
pnpm dev:server # Server only
pnpm build # Build all
pnpm typecheck # Type checking
pnpm test:run # Run tests
pnpm db:generate # Generate DB migration
pnpm db:migrate # Apply migrations
See doc/DEVELOPING.md for the full development guide.
Roadmap
- ✅ Plugin system (e.g. add a knowledge base, custom tracing, queues, etc)
- ✅ Get OpenClaw / claw-style agent employees
- ✅ companies.sh - import and export entire organizations
- ✅ Easy AGENTS.md configurations
- ✅ Skills Manager
- ✅ Scheduled Routines
- ✅ Better Budgeting
- ⚪ Artifacts & Deployments
- ⚪ CEO Chat
- ⚪ MAXIMIZER MODE
- ⚪ Multiple Human Users
- ⚪ Cloud / Sandbox agents (e.g. Cursor / e2b agents)
- ⚪ Cloud deployments
- ⚪ Desktop App
Community & Plugins
Find Plugins and more at awesome-paperclip
Telemetry
Paperclip collects anonymous usage telemetry to help us understand how the product is used and improve it. No personal information, issue content, prompts, file paths, or secrets are ever collected. Private repository references are hashed with a per-install salt before being sent.
Telemetry is enabled by default and can be disabled with any of the following:
| Method | How |
|---|---|
| Environment variable | PAPERCLIP_TELEMETRY_DISABLED=1 |
| Standard convention | DO_NOT_TRACK=1 |
| CI environments | Automatically disabled when CI=true |
| Config file | Set telemetry.enabled: false in your Paperclip config |
Contributing
We welcome contributions. See the contributing guide for details.
Community
- Discord — Join the community
- GitHub Issues — bugs and feature requests
- GitHub Discussions — ideas and RFC
License
MIT © 2026 Paperclip
Star History
Open source under MIT. Built for people who want to run companies, not babysit agents.