Open-source Python framework for orchestrating role-based autonomous AI agents (Crews) and event-driven workflows (Flows).
- Stars
- 104,571
- Forks
- 17,445
- Open issues
- 6,220
- Last commit
- 22 hours ago
What is it?
Paperclip is a Node.js server and React UI for running a team of AI agents toward business goals. You bring your own agents, such as Claude Code, Codex, Cursor, Gemini CLI, OpenClaw or HTTP-based bots, and assign them goals and tasks from one dashboard. Each agent can use its own model and runtime while tasks, skills, permissions and history stay in a single place.
The app is organized around an org chart with roles, reporting lines and budgets, plus task threads with comments, documents and run history. It tracks token and cost spend by company, agent, project and model, sends threshold alerts, and can pause work at configured limits. Approval stages, agent pause and resume, and revisioned configuration changes provide governance.
Paperclip also includes scheduled routines triggered by cron, webhooks or an API, a skill editor with saved test inputs, a plugin system, company import and export, and support for multiple organizations in one deployment. Locally it starts with an embedded PostgreSQL database; for production you can point it at your own Postgres.
Key features
- 01Org chart with roles, reporting lines and per-agent budgets
- 02Works with Claude Code, Codex, Cursor, Gemini CLI, OpenClaw and HTTP bots
- 03Task threads with comments, documents, attachments and run history
- 04Token and cost tracking with budget thresholds and automatic pauses
- 05Scheduled routines triggered by cron, webhooks or API
- 06Skill editor and shared skills with version history
Use cases
- Running several coding agents on a shared backlog without losing track of who is doing what
- Setting spend limits and alerts for autonomous agents that run continuously
- Automating recurring jobs such as support triage, reports or social posts with audit history
- Managing multiple agent-run businesses or teams from a single self-hosted deployment
Things to know
- The README excerpt gives no install or run commands; its quickstart section is not included here.
- Agent Chat and the chat and email connectors are experimental and must be enabled in instance settings.
- It is self-hosted, so you run and maintain the Node.js server and React UI yourself; a hosted Paperclip Cloud is only on a waitlist.
Topics
FAQ
- What is paperclip?
- Self-hosted Node.js and React app for orchestrating teams of AI agents, with org charts, task tracking, budgets and governance. Paperclip is a Node.js server and React UI for running a team of AI agents toward business goals. You bring your own agents, such as Claude Code, Codex, Cursor, Gemini CLI, OpenClaw or HTTP-based bots, and assign them goals and tasks from one dashboard. Each agent can use its own model and runtime while tasks, skills, permissions and history stay in a single place.
- Is paperclip free to use? What license does it have?
- paperclip is open source under the MIT license. Check the license terms before using it in commercial products.
- Is paperclip still maintained?
- Actively maintained. The last commit to paperclip was on Oct 19, 2026.
- What can I use paperclip for?
- Running several coding agents on a shared backlog without losing track of who is doing what Setting spend limits and alerts for autonomous agents that run continuously Automating recurring jobs such as support triage, reports or social posts with audit history Managing multiple agent-run businesses or teams from a single self-hosted deployment
- Where can I get paperclip?
- The source code and installation instructions are on GitHub: https://github.com/paperclipai/paperclip
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Self-hosted personal AI agent framework in Python with a browser WebUI, terminal client, chat app channels, tools, memory and MCP support.
Open-source agent runtime and terminal TUI for long-horizon research and file-based work, with ReAct and parallel Agent Team modes.
Open-source personal AI assistant and Agent Harness that plans tasks, runs tools and skills, and keeps memory across web and IM channels.
An agent-native, self-hostable AI learning workspace for personalized tutoring, Q&A, quizzes, research and visualization, built on Python and Next.js.
Python framework for building autonomous AI agents that research, plan, code and run tasks, with memory, RAG and 100+ LLM providers.