Logo
Deploy Now

SaaS Alternative

Relevance AI

Categories

Developer Tools Automation Task Management Orchestration Workflow Engine AI Agent Management Machine Learning Operations

Stars

79,080

Forks

14,495

Watchers

382

Developer links

Last Updated: 08-21-2026 06:48 PM (UTC)

Paperclip

With over 77,000 GitHub stars accumulated in under five months since its March 2026 launch, Paperclip has become the default control plane for teams running multiple AI agents in production. Rather than juggling dozens of terminal tabs with Claude Code sessions, Codex instances, and Gemini CLI workers, Paperclip organizes all agents into a company structure with org charts, reporting lines, role-based permissions, and per-agent monthly budgets that trigger hard-stops when exceeded. The platform supports any runtime through its adapter system — Process adapters manage local CLI agents like Claude Code, Codex, Cursor, Pi, and OpenCode as child processes, while HTTP adapters trigger remote agents via webhooks to OpenClaw, serverless platforms, or custom endpoints. Heartbeat-based execution wakes agents on configurable schedules, injecting goal context, budget state, and workspace paths directly into the invocation payload. The Work and Task System provides atomic checkout with execution locks, first-class blocker dependencies, and structured work products to eliminate duplicate effort. Governance features include approval workflows, decision tracking, emergency stops, and full audit trails tracing every mutation to an actor. Deployment runs as a single Node.js process with embedded PostgreSQL locally or scales to external Postgres for production, installable in one command via npx paperclipai onboard. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Paperclip
Paperclip
Paperclip
Paperclip
Paperclip

Benefits

  • Model-Agnostic Agent Runtime Support
  • Connect Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and any HTTP-accessible agent through built-in Process and HTTP adapters without vendor lock-in to a single provider.
  • Per-Agent Budget Hard-Stops
  • Set monthly spending limits per agent with automatic hard-stops when budgets are exceeded, providing granular cost visibility and preventing runaway API consumption across your agent fleet.
  • Complete Governance and Audit Trail
  • Every mutation traced to an actor with approval workflows, decision tracking, emergency stops, and role-based access control enforcing organizational policies across all agent operations.
  • One-Command Self-Hosted Deployment
  • Install via npx paperclipai onboard with interactive setup, embedded PostgreSQL for local development, or connect to external Postgres for production with no cloud account required.

Features

  • Heartbeat Execution
  • DB-backed wakeup queue triggers agents on configurable schedules with budget checks, workspace resolution, secret injection, and structured audit logging per run.
  • Org Chart Management
  • Define roles, titles, reporting lines, permissions, and budgets per agent in a hierarchical structure mirroring real organizational teams.
  • Plugin System
  • Extend functionality through out-of-process workers with capability-gated host services, job scheduling, tool exposure, and UI contributions without forking core.
  • Task Orchestration
  • Atomic checkout with execution locks, first-class blocker dependencies, company-goal-project task hierarchy, and structured work products preventing duplicate effort.
  • MCP Integration
  • The @paperclipai/mcp-server package exposes the full REST API as MCP tools, enabling agent management through Claude Desktop or any MCP-compatible client.