diff --git a/README.md b/README.md new file mode 100644 index 00000000..aecb30ea --- /dev/null +++ b/README.md @@ -0,0 +1,265 @@ +

+ + Paperclip +

+ +

The control plane for autonomous AI companies.

+ +

+ Open-source orchestration to manage teams of AI agents.
+ Hire AI employees, set goals, automate jobs — your business runs itself. +

+ +

+ Quickstart · + Docs · + GitHub · + Discord +

+ +

+ MIT License + Stars + Discord +

+ +
+ + +

+ [demo video placeholder] +

+ +
+ +## What is Paperclip? + +### **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. + +**Three steps to an autonomous company:** + +| | 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
OpenClaw		Claude
Claude Code		Codex
Codex		Cursor
Cursor		Bash
Bash		HTTP
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 Agent + +Your Claude, Cursor, Codex, and OpenClaw — organized under one org structure, pointed at one goal. If it can receive a heartbeat, it's hired. + +### Goal Alignment + +Every piece of work traces back to the company mission. Your agents know _what_ to do and _why_. + +``` +Company Mission → Project Goal → Agent Goal → Task +``` + +### Heartbeats + +Agents wake up on a schedule, check their work, and act. Delegation flows up and down the org chart. Ticket assignments wake agents. Cross-team requests delegate to the best agent for the job. + +### Cost Control + +Every agent gets a monthly budget. When they hit it, they stop. No runaway costs. No surprise bills. Track costs per agent, per task, per project, per goal. + +### Multi-Company + +One deployment. Many companies. Run one AI company or fifty with complete data isolation. One control plane for your entire portfolio. + +### Ticket System + +Every conversation traced. Every decision explained. Structured tickets with clear owners, full tool-call tracing, and an immutable audit log. Nothing happens in the dark. + +### Governance + +You're the board. Approve hires. Approve strategy. Override anything. Agents can't hire new agents or execute strategies without your sign-off. Pause, resume, reassign, terminate — at any time. + +
+ +## 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. | + +
+ +## Quickstart + +Open source. Self-hosted. No Paperclip account required. + +```bash +npx paperclip onboard +``` + +Or manually: + +```bash +git clone https://github.com/paperclip-dev/paperclip.git +cd paperclip +pnpm install +pnpm dev +``` + +This starts the API server at `http://localhost:3100` and the UI at `http://localhost:5173`. An embedded PostgreSQL database is created automatically — no setup required. + +### With Docker + +```bash +docker compose up --build +``` + +> **Requirements:** Node.js 20+, pnpm 9.15+ + +
+ +## Architecture + +``` +┌──────────────────────────────────────────────────────┐ +│ You (the board) │ +├──────────────────────────────────────────────────────┤ +│ Paperclip (control plane) │ +│ │ +│ Dashboard · Org Chart · Tasks · Goals · Budgets │ +│ Approvals · Activity Log · Cost Tracking │ +├──────────────────────────────────────────────────────┤ +│ Adapters │ +│ │ +│ Claude · OpenClaw · Codex · Cursor · HTTP │ +└──────────────────────────────────────────────────────┘ +``` + +Paperclip is the **control plane**, not the execution plane. Agents run wherever they run and phone home. Adapters connect Paperclip to any execution environment. + +**Stack:** TypeScript · Express · React 19 · PostgreSQL · Drizzle ORM · TailwindCSS + +
+ +## FAQ + +**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. + +**Can I use my existing agents?** +Yes. Paperclip is unopinionated about agent runtimes. Your agents can be Claude Code sessions, OpenClaw bots, Python scripts, shell commands, HTTP webhooks — anything that can receive a heartbeat signal. Adapters connect Paperclip to whatever execution environment you use. + +**What happens when an agent hits its budget limit?** +The agent auto-pauses and new tasks are blocked. You get a soft warning at 80%. As the board, you can override the limit at any time. + +**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. + +**Can I run multiple companies?** +Yes. A single deployment can run dozens of companies with complete data isolation. Useful for separate ventures, testing strategies in parallel, or templating org configs for reuse. + +**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. + +
+ +## Comparison + +| | Paperclip | Agent frameworks (LangChain, CrewAI) | Single-agent tools (Claude Code, Cursor) | +| -------------------------- | --------- | ------------------------------------ | ---------------------------------------- | +| Multi-agent orchestration | Yes | Partial | No | +| Org structure & hierarchy | Yes | No | No | +| Cost control & budgets | Yes | No | No | +| Goal alignment | Yes | No | No | +| Governance & approvals | Yes | No | No | +| Multi-company | Yes | No | No | +| Agent-agnostic | Yes | Framework-locked | Single provider | +| Ticket-based work tracking | Yes | No | No | + +
+ +## Development + +```bash +pnpm dev # Full dev (API + UI) +pnpm dev:server # Server only +pnpm dev:ui # UI 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](doc/DEVELOPING.md) for the full development guide. + +
+ +## Contributing + +We welcome contributions. See the [contributing guide](CONTRIBUTING.md) for details. + + + +
+ +## Community + +- [Discord](https://discord.gg/paperclip) — chat, questions, show & tell +- [GitHub Issues](https://github.com/paperclip-dev/paperclip/issues) — bugs and feature requests +- [GitHub Discussions](https://github.com/paperclip-dev/paperclip/discussions) — ideas and RFC + +
+ +## License + +MIT © 2026 Paperclip + +
+ +--- + +

+ Open source under MIT. Built for people who want to run companies, not babysit agents. +

diff --git a/doc/README-draft.md b/doc/README-draft.md new file mode 100644 index 00000000..a8a65d3b --- /dev/null +++ b/doc/README-draft.md @@ -0,0 +1,78 @@ +# Instructions for writing the README.md + +The readme should be visually interesting, to the point, not too long. +Use the copy from the website in cases where we need some. + +- gives the pitch why, e.g. from the homepage. + +## Outline + +- image header up top +- Paperclip +- Manage autonomous AI Businesses +- The open-source AI-agent orchestrator teams of agents that run companies + +- a video + +# What is it + +Paperclip is a node server & UI that orchestrates a team of agents to run businesses. + +Bring-your-own agents, assign goals, and track your agent's work and costs. + +It looks like a task manager but has specialized skills and agent coordination + +**It's high taste, and feels good to use** + +# Paperclip is right for you if: + +- You want to build autonomous companies +- You want to coordinate many different types agents (OpenClaw, Codex, Claude, Cursor, etc.) to collaborate towards a common goal +- You have 20 simultaneous Claude Code terminals open (and lose track of what everyone is working on) +- You want to let your agents run autonomously 24/7, but still audit their work and chime in when needed +- You want to monitor costs +- You want a process for managing your agents that feels like using a task manager +- You want to manage your autonomous businesses from your phone + +# What is not + +Paperclip is not: + +- a code review tool +- opinionated about what agent you use + +# the problem + +If you want to be maximally effective with agents, you need to + +# quickstart + +# faq + +# comparison + +# contributing + +# community + +# license + +# footer + +## Examples: + +- https://github.com/klawsh/klaw.sh - nice header, nice tables + - what is it + - the problem + - quickstart + - faq + - comparison + - contributing + - community + - license + - footer +- https://github.com/nearai/ironclaw - nice header + - philosophy +- https://github.com/TinyAGI/tinyclaw - nice header, nice video +- https://github.com/ryoppippi/ccusage - nice header, +- https://github.com/can1357/oh-my-pi - a little long diff --git a/doc/assets/logos/bash.svg b/doc/assets/logos/bash.svg new file mode 100644 index 00000000..35f5d54c --- /dev/null +++ b/doc/assets/logos/bash.svg @@ -0,0 +1,5 @@ + + + + + diff --git a/doc/assets/logos/claude.svg b/doc/assets/logos/claude.svg new file mode 100644 index 00000000..f43c74a5 --- /dev/null +++ b/doc/assets/logos/claude.svg @@ -0,0 +1,3 @@ + + + diff --git a/doc/assets/logos/codex.svg b/doc/assets/logos/codex.svg new file mode 100644 index 00000000..73335c4e --- /dev/null +++ b/doc/assets/logos/codex.svg @@ -0,0 +1,4 @@ + + + + diff --git a/doc/assets/logos/cursor.svg b/doc/assets/logos/cursor.svg new file mode 100644 index 00000000..3078b358 --- /dev/null +++ b/doc/assets/logos/cursor.svg @@ -0,0 +1,4 @@ + + + + diff --git a/doc/assets/logos/http.svg b/doc/assets/logos/http.svg new file mode 100644 index 00000000..de03e00b --- /dev/null +++ b/doc/assets/logos/http.svg @@ -0,0 +1,7 @@ + + + + + + + diff --git a/doc/assets/logos/openclaw.svg b/doc/assets/logos/openclaw.svg new file mode 100644 index 00000000..7b29617d --- /dev/null +++ b/doc/assets/logos/openclaw.svg @@ -0,0 +1,17 @@ + + + + + + + + + + + + + + + + +