175 listed
Harnesses & SDKs
Frameworks and SDKs for building agents: the Claude Agent SDK, OpenAI Agents SDK, LangGraph, CrewAI and many more. Each page lists languages, packages, MCP and A2A support and how it orchestrates agents, with a link to the page every fact came from.
Showing 73–79 of 79
| Name | Language | Stars | Downloads / month (approx.) | MCP | A2A | Multi-agent |
|---|---|---|---|---|---|---|
| Upsonic Python framework for autonomous agents that work in a sandboxed workspace, and task agents with tools and MCP support. | Python | 8K | ~1K | Built in | Not stated | Yes |
| mcp-agent Python framework for MCP-based agents with composable workflow patterns, MCP server creation and Temporal-backed durable execution. | Python | 8.6K | ~65.2K | Built in | Not stated | Yes |
| OpenAI Swarm Experimental Python library that teaches agent handoffs on the Chat Completions API; OpenAI now points users to its Agents SDK. | Python | 22.1K | — | Not stated | Not stated | Yes |
| blades Go framework for multimodal AI agents with models, tools, memory, middleware, chains and structured output. | Go | 819 | — | Not stated | Not stated | Yes |
| MetaGPT Python multi-agent framework that gives LLM agents software-company roles and SOPs to turn a one-line requirement into a project repository. | Python | 71K | ~2.7K | Not stated | Not stated | Yes |
| Lagent Lightweight Python framework for LLM agents built as PyTorch-style layers, with agent memory kept as session state. | Python | 2.3K | ~1.5K | Not stated | Not stated | Yes |
| Youtu-Agent Framework for building, running and evaluating autonomous agents, with a planner-based multi-agent mode, skills and agent RL training. | Python | 4.6K | ~99 | Not stated | Not stated | Yes |