A curated list of awesome LLM frameworks and agent development tools. If you have a suggestion, feel free to open an issue or pull request. (Last updated: 2025-09-07)
-
CrewAI - Framework for orchestrating role-playing AI agents
37,756 stars · 4,979 forks · 260 contributors · 162 issues · Python · MIT
- Role-based agent design
- Multi-agent collaboration
- Flexible memory system
- Built-in error handling
-
Langchain - Building applications with LLMs through composability
114,932 stars · 18,883 forks · 472 contributors · 408 issues · Jupyter Notebook · MIT
- Modular and extensible architecture
- Unified interface for LLMs
- Pre-built agent toolkits
- CSV, JSON, and SQL agents
- Python and Pandas integration
- Vector store capabilities
-
Microsoft AutoGen - Framework for building multi-agent conversational systems
49,476 stars · 7,558 forks · 446 contributors · 486 issues · Python · CC-BY-4.0
- Multi-agent architecture
- Customizable agents
- Code execution support
- Flexible human involvement
- Advanced conversation management
-
Llama Index - Data framework for LLM applications
44,095 stars · 6,339 forks · 475 contributors · 266 issues · Python · MIT
- Advanced indexing and retrieval
- Support for 160+ data sources
- Customizable RAG workflows
- Structured data handling
- Query optimization
-
Microsoft Semantic Kernel - Integration framework for AI models
26,056 stars · 4,191 forks · 372 contributors · 544 issues · C# · MIT
- Enterprise-grade security
- Multi-language support
- Plugin architecture
- Responsible AI features
- Memory management
-
Dify - Open-source framework for LLM applications
113,276 stars · 17,351 forks · 466 contributors · 702 issues · TypeScript · NOASSERTION
- Visual prompt orchestration
- Long context integration
- API-based development
- Multi-model support
- RAG pipeline
-
Haystack - End-to-end NLP framework
22,137 stars · 2,332 forks · 292 contributors · 121 issues · Python · Apache-2.0
- Document processing
- Neural search
- Question answering
- Semantic search
- Agent capabilities
-
Embedchain - Framework for ChatGPT-like bots
39,447 stars · 4,132 forks · 226 contributors · 488 issues · Python · Apache-2.0
- Multi-source data ingestion
- Automated embedding
- Context window management
- Multiple LLM support
- RAG optimization
-
SuperAGI - Open-source autonomous AI agent framework
16,690 stars · 2,064 forks · 63 contributors · 201 issues · Python · MIT
- Customizable agent workflows
- Tool creation framework
- Performance monitoring
- Resource management
- Multi-vector memory storage
-
AGiXT - Scalable framework for AI agents
3,075 stars · 427 forks · 41 contributors · 3 issues · Python · MIT
- Multi-provider support
- Chain of thought processing
- Extensible plugin system
- Command chaining
- Web UI included
-
XAgent - Autonomous LLM-based agent framework
8,436 stars · 895 forks · 33 contributors · 54 issues · Python · Apache-2.0
- Human-like planning
- Autonomous task decomposition
- Tool learning capabilities
- Advanced error recovery
- Built-in action validation
-
OpenAgents - Open platform for language agents
4,438 stars · 486 forks · 16 contributors · 12 issues · Python · Apache-2.0
- Data analysis capabilities
- Web browsing integration
- Coding assistance
- Plugin ecosystem
- Interactive visualization
-
AI Legion - Swarm framework for autonomous agents
1,421 stars · 172 forks · 6 contributors · 8 issues · TypeScript · MIT
- Multi-agent coordination
- Dynamic task allocation
- Emergent behavior support
- Flexible agent roles
- Real-time collaboration
-
Agent Protocol - Unified interface for AI agents
1,433 stars · 160 forks · 15 contributors · 42 issues · Python · MIT
- Standardized communication
- Language-agnostic design
- Tool integration specs
- Interoperability focus
- Protocol versioning
-
Agents.js - JavaScript framework for building AI agents
- Browser-native implementation
- Event-driven architecture
- Tool abstraction layer
- Memory management
- Real-time processing- CAMEL - Communicative Agents for "Mind" Exploration
6,380 stars · 762 forks · 76 contributors · 305 issues · Python · Apache-2.0
-
Role-playing framework
-
Task-oriented dialogue
-
Multi-agent conversations
-
Behavioral analysis
-
Cognitive architecture- BabyAGI - Lightweight framework for AI task management
-
Task prioritization
-
Autonomous execution
-
Memory persistence
-
Goal-oriented planning
-
Resource optimization- Autonomous-GPT - Framework for autonomous GPT-4 agents
171,792 stars · 45,107 forks · 438 contributors · 201 issues · Python · NOASSERTION
- Internet access capabilities
- Long-term memory
- Goal-oriented behavior
- File operations
- Command execution- MetaGPT - Multi-agent framework for software development
52,472 stars · 6,208 forks · 116 contributors · 89 issues · Python · MIT
-
Role-based development
-
Code generation
-
Project management
-
Documentation writing
-
Testing automation- minions - Extensible framework for AI assistants
-
Custom behavior definition
-
Tool integration
-
State management
-
Event handling
-
Parallel execution- ix - Autonomous agent framework
1,018 stars · 125 forks · 5 contributors · 14 issues · Python · MIT
- Visual workflow builder
- Sandbox environments
- Tool integration
- Process monitoring
- Agent collaboration- saplings - Build smarter agents using tree search
230 stars · 13 forks · 3 contributors · 2 issues · Python · Apache-2.0
- Boost reasoning abilities
- Supports popular search algorithms
- Minimal setup, 2 lines of code- Smolagents - Minimalist framework for building powerful agents
16,448 stars · 1,446 forks · 123 contributors · 209 issues · Python · Apache-2.0
- Code-first approach
- Multi-agent orchestration
- LLM provider flexibility
- Tool integration
- Hub integration for sharing- Flowise - Drag & drop UI framework for building LLM flows
37,674 stars · 19,592 forks · 213 contributors · 600 issues · TypeScript · Apache-2.0
- Visual flow builder
- Custom LLM integrations
- API generation
- Authentication support
- Docker deployment- Pydantic AI - Production-grade agent framework built on Pydantic
9,574 stars · 854 forks · 117 contributors · 297 issues · Python · MIT
- Type-safe development
- Multi-model support
- Structured responses
- Dependency injection
- Logfire integration- Upsonic - Reliable agent framework that support MCP.
7,517 stars · 698 forks · 24 contributors · 53 issues · Python · MIT
- Easy-to-activate reliability layers
- Model Context Protocol (MCP)
- Integrated Browser Use and Computer Use
- Isolated environment to run agents
- Task-Centric Design