Open source frameworks for building AI agents — multi-agent orchestration, tool calling, and autonomous workflows.
Ranked by Coldcast Score. Updated weekly.
The agent engineering platform
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Run OpenClaw more securely inside NVIDIA OpenShell with managed inference
Use Garry Tan's exact Claude Code setup: 15 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
The agent engineering platform
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
ClawTeam: Agent Swarm Intelligence (One Command → Full Automation)
AI skills framework by MiniMax for building task-specific AI agents.
Framework for orchestrating autonomous AI agents
Build resilient language agents as graphs
AI orchestration framework for production LLM apps
Claude Code skills that turn any codebase into an interactive knowledge graph you can explore, search, and ask questions about (Multi-platform e.g., Codex are supported).
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
A collection of 130+ specialized Codex subagents covering a wide range of development use cases.
Give your AI agent access to your live Chrome session — works out of the box, connects to tabs you already have open
A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention
Programming framework for agentic AI
Turn OpenClaw from a black box into a local control center you can see, trust, and control.
AI generates editable, beautifully designed PPTX from any document — no design skills needed | 15 examples, 229 pages
Your personal intelligence agent. Watches the world from multiple data sources and pings you when something changes.