Stars
🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
LlamaIndex is the leading document agent and OCR platform
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
AgentFlow: In-the-Flow Agentic System Optimization
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
This is the official repo for "PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization". PromptAgent is a novel automatic prompt optimization method that auton…
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
torchcomms: a modern PyTorch communications API
Scalable toolkit for efficient model reinforcement
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Collection of evals for Inspect AI
DSPy: The framework for programming—not prompting—language models
FrugalGPT: better quality and lower cost for LLM applications
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
Reliable Multi-Agent Orchestration Framework
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
(ACL 2025 Main) Code for MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents https://www.arxiv.org/pdf/2503.01935
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
The absolute trainer to light up AI agents.
[ICML'25 Oral] Multi-agent Architecture Search via Agentic Supernet
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A PyTorch native platform for training generative AI models