LLM and AI Agent Frameworks 🖼️
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
🧠🔗 From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices
Production-ready platform for agentic workflow development.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
🦜🔗 Build context-aware reasoning applications
Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Build Conversational AI in minutes ⚡️
Memory for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
Agent Framework / shim to use Pydantic with LLMs
Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning.
Lightweight coding agent that runs in your terminal
Open source AI coding agent. Designed for large projects and real world tasks.
Lightweight coding agent that runs in your terminal
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
The AI browser automation framework
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
The open-source backbone for LLM agents that stay under control as you scale their complexity.