Everything in the catalog

Python framework for autonomous agents that work in a sandboxed workspace, and task agents with tools and MCP support.

Python framework for MCP-based agents with composable workflow patterns, MCP server creation and Temporal-backed durable execution.

Experimental Python library that teaches agent handoffs on the Chat Completions API; OpenAI now points users to its Agents SDK.

Go framework for multimodal AI agents with models, tools, memory, middleware, chains and structured output.

Python multi-agent framework that gives LLM agents software-company roles and SOPs to turn a one-line requirement into a project repository.

Lightweight Python framework for LLM agents built as PyTorch-style layers, with agent memory kept as session state.

Framework for building, running and evaluating autonomous agents, with a planner-based multi-agent mode, skills and agent RL training.