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: 2025-02-16)
-
CrewAI - Framework for orchestrating role-playing AI agents
26,582 stars · 3,595 forks · 202 contributors · 159 issues · Python · MIT
- Role-based agent design
- Multi-agent collaboration
- Flexible memory system
- Built-in error handling
-
Langchain - Building applications with LLMs through composability
100,556 stars · 16,332 forks · 481 contributors · 424 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
39,516 stars · 5,802 forks · 417 contributors · 563 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
38,928 stars · 5,557 forks · 478 contributors · 718 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
23,083 stars · 3,495 forks · 321 contributors · 402 issues · C# · MIT
- Enterprise-grade security
- Multi-language support
- Plugin architecture
- Responsible AI features
- Memory management
-
Dify - Open-source framework for LLM applications
67,511 stars · 9,865 forks · 476 contributors · 420 issues · TypeScript · NOASSERTION
- Visual prompt orchestration
- Long context integration
- API-based development
- Multi-model support
- RAG pipeline
-
Haystack - End-to-end NLP framework
19,206 stars · 2,050 forks · 263 contributors · 119 issues · Python · Apache-2.0
- Document processing
- Neural search
- Question answering
- Semantic search
- Agent capabilities
-
Embedchain - Framework for ChatGPT-like bots
24,606 stars · 2,282 forks · 155 contributors · 245 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
15,872 stars · 1,903 forks · 62 contributors · 187 issues · Python · MIT
- Customizable agent workflows
- Tool creation framework
- Performance monitoring
- Resource management
- Multi-vector memory storage
-
AGiXT - Scalable framework for AI agents
2,894 stars · 387 forks · 38 contributors · 8 issues · Python · MIT
- Multi-provider support
- Chain of thought processing
- Extensible plugin system
- Command chaining
- Web UI included
-
XAgent - Autonomous LLM-based agent framework
8,148 stars · 863 forks · 34 contributors · 52 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
4,129 stars · 456 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
1,368 stars · 159 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
1,094 stars · 137 forks · 15 contributors · 37 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
6,304 stars · 750 forks · 72 contributors · 319 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
171,513 stars · 45,046 forks · 438 contributors · 207 issues · Python · NOASSERTION
- Internet access capabilities
- Long-term memory
- Goal-oriented behavior
- File operations
- Command execution
-
MetaGPT - Multi-agent framework for software development
46,213 stars · 5,505 forks · 115 contributors · 78 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
1,019 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
214 stars · 11 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
10,677 stars · 1,010 forks · 97 contributors · 167 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
35,126 stars · 18,296 forks · 190 contributors · 481 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
6,377 stars · 496 forks · 58 contributors · 117 issues · Python · MIT
- Type-safe development
- Multi-model support
- Structured responses
- Dependency injection
- Logfire integration