AI Agent Frameworks

Agent Skills defines a specification and documentation for giving AI agents reusable capabilities.

Uplizd Unicorn offers visual AI tools for startups and small businesses to build and optimize business content.

Pydantic AI provides Python tools for building agents with voice, image generation, and embedding capabilities.

BabyAGI explores task planning as a method for developing autonomous agents.

The open-multi-agent project provides a self-hosted TypeScript runtime with approvals and verifiable records.

MCP Memory Service provides persistent memory for AI agent pipelines through an API and knowledge graph.

Steel Browser provides a browser API and sandbox for automating web tasks with AI agents.

AgentForge: AI agent framework for building, customizing, and deploying cognitive architectures and multi-agent systems.

SuperAGI provides tools for developers to build, manage, and run autonomous AI agent systems.

Swarms provides an enterprise oriented framework for coordinating multiple AI agents.

Langflow supports building and deploying agent workflows through a visual development environment.

Pydantic AI provides Python tools for agents, realtime voice, image generation, and embeddings.

The Contexto project provides a context engine designed for long running AI agents.

Hive supports applications that coordinate multiple AI agents through shared task workflows.

This repository catalogs SDKs, frameworks, libraries, and tools for building and operating AI agents.

Build AI agents and multi-agent workflows in.NET, Python, and Go with Microsoft Agent Framework.

Mastra provides a TypeScript framework for creating AI applications and agent workflows.

Strands Agents SDK provides an open source toolkit for building and controlling production agents in Python and TypeScript.

PraisonAI supports agents that research, plan, code, and execute tasks, with memory and RAG features.

CAMEL provides a framework for building and researching systems with multiple AI agents.

Maestro Orchestrate coordinates specialists and parallel agents across coding tools, with code review and debugging features.

agency-swarm provides a framework for orchestrating multiple AI agents.

Maestro demonstrates AI-assisted task breakdown and execution by orchestrating Claude subagents.

Langroid supports programming multi-agent systems with large language models.