awesome-ai-agents
github.com/nipunaranasinghe/awesome-ai-agents ↗A curated list of frameworks, tools, and resources for building and deploying AI agents. From multi-agent systems to autonomous coding assistants, this repository covers the latest advancements in AI agent technology. Perfect for developers, researchers, and AI enthusiasts exploring the future of autonomous systems.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me 🔌 protocols resources from awesome-ai-agents"
Installation instructions →What's inside
⚙️ Agent Operations
- A2A🔌 Protocols
Open protocol started by Google for agent-to-agent communication across frameworks
- AgentBench📊 Evaluation
Multi-environment testing for agents
- Agent Evaluation📊 Evaluation
Benchmarking agent capabilities
- Agent Governance Toolkit🔒 Security & Governance
Policy enforcement, zero-trust identity, and execution sandboxing for autonomous AI agents
- agenttrace📊 Evaluation
Local TUI and reports for AI coding agent session cost, latency, failures, and health
- Arize Phoenix📈 Observability
Open-source AI observability with OpenTelemetry tracing, evals, and agent debugging
🌟 Core Frameworks
- Agency Swarm
Reliable multi-agent orchestration using OpenAI Assistants API
- AgentField
Open-source control plane for AI agents at scale, with routing, memory, observability, identity, and auth
- AgentOps
Monitoring, cost tracking, and benchmarking SDK for agents
- Agentset
Production-ready RAG platform with agentic reasoning, hybrid search, and multimodal support
- AgentVerse
Multi-agent simulation environments for research
- AGiXT
Adaptive automation platform with persistent memory
📚 Research & Benchmarks
- Agentic AI Systems📄 Papers
Components and applications of agentic AI
- A Survey on LLM-based Autonomous Agents📄 Papers
Focus on autonomous LLM agents
- Large Language Model based Multi-Agents📄 Papers
Survey of progress and challenges
- Multi-Agent Collaboration📄 Papers
Collaboration in multi-agent systems
- OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents📄 Papers
Four-agent pipeline with bandit scheduling turns optimization problems into solver code
- PerspectiveGap📊 Benchmarks
Benchmark for writing orchestration prompts in multi-agent systems, 110 scenarios across 10 topologies
🚀 Specialized Agents
- AgenticSeek💻 Coding Agents
Fully local autonomous agent that browses web and codes without APIs
- Agent S🌐 Web & Computer Use Agents
Open framework for computer-use agents that operate desktop GUIs like a human
- Agon🔬 Research Agents
Prompt Economy orchestrator: reusable scientist/coder/auditor loops instead of per-task prompts, 18 roles, 10+ disciplines
- Aider💻 Coding Agents
AI pair programming in terminal
- AI-town🎨 Creative Agents
Virtual world simulation with AI agents
- AnythingLLM🗣️ Programming Language Agents
All-in-one AI agent builder with RAG and UI
🌐 Community Resources
- AgentOps Discord👥 Communities
Developer space for observability and testing agents
- AutoGen Discussions👥 Communities
Microsoft AutoGen community forum
- LangChain Community👥 Communities
Active developer community
- Letta AI Community👥 Communities
Discussions on adaptive memory in AI agents
- The Batch (DeepLearning.AI)📰 Newsletters
Weekly AI industry insights
Contributing
Showing a sample of 128 resources. View the full list on GitHub →