Multi-agent workspace where teams hire reusable "digital employees" — an orchestrator runs specialists in parallel and returns finished decks, dashboards, reports and Excel files.
What is Paperclip?
Open-source, self-hosted control plane that runs teams of AI agents like a company, with org charts, tasks, budgets and approvals.
- Pricing
- Free
- Free plan
- Yes
- Category
- Automation & Workflows
- Made by
- Paperclip
- Released
- Updated
Paperclip screenshots
Paperclip features & details
Paperclip is a self-hosted Node.js server and React dashboard for managing many AI agents at once. It looks like a task manager, but underneath it models a company: you set a goal, "hire" agents into roles on an org chart (CEO, engineers, marketers), and they pick up ticketed tasks, delegate up and down the hierarchy, and report back in threaded conversations that survive reboots.
It is agent-agnostic. Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Pi, OpenClaw, Hermes and other harnesses plug in through adapters, and anything that can receive a heartbeat can be added, with the model and harness chosen per agent. Around them Paperclip supplies the management layer: company, project and agent budgets with spend tracking and automatic pauses, review and approval gates, scheduled routines triggered by cron, API or webhook, a skills studio for writing and testing shared skills, artifacts with inline comments, connections to GitHub, Notion, Railway or your own MCP servers, and multi-organisation separation in one deployment. Experimental agent chat and Slack, Discord and Telegram connectors are available behind settings.
Paperclip is MIT-licensed and free; it runs locally with npx paperclipai onboard and needs no Paperclip account, only the API keys or subscriptions your agents use. A hosted Paperclip Cloud is on a waitlist.
No reviews yet — sign in to write the first one
Apps similar to Paperclip
The closest matches are MagiCrew and AutoGPT. See every Paperclip alternative compared by price and free plan.
AI agent platform where a coordinator called Otto runs AI "Experts" and scheduled workflows, available in the cloud or self-hosted.
MIT-licensed multi-agent harness that turns the CLI coding agent you already use into a persistent clone of yourself, running around the clock.
Open-source, self-hostable managed agent platform: run durable AI agents on any model and any machine through one API, CLI and SDK.
Open-source, MIT-licensed visual builder for AI agents, RAG apps and MCP servers, maintained by IBM's DataStax and extensible in Python.