OpenPipe / ARTLinks
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!
☆8,534Updated this week
Alternatives and similar repositories for ART
Users that are interested in ART are comparing it to the libraries listed below
Sorting:
- Our library for RL environments + evals☆3,791Updated this week
- Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs☆2,171Updated 4 months ago
- ☆10,372Updated 5 months ago
- DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solvin…☆3,102Updated 4 months ago
- 100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.☆3,994Updated last week
- Optimize prompts, code, and more with AI-powered Reflective Text Evolution☆2,214Updated this week
- The absolute trainer to light up AI agents.☆14,144Updated this week
- Memory for AI Agents in 6 lines of code☆11,703Updated this week
- Build effective agents using Model Context Protocol and simple workflow patterns☆7,988Updated last week
- Post-training with Tinker☆2,805Updated this week
- Supercharge Your LLM with the Fastest KV Cache Layer☆6,839Updated this week
- 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG☆11,274Updated last week
- Python library for Agentic Document Extraction from LandingAI☆2,343Updated last week
- Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, an…☆8,936Updated this week
- "RAG-Anything: All-in-One RAG Framework"☆12,460Updated last week
- LLM agents built for control. Designed for real-world use. Deployed in minutes.☆17,639Updated last week
- Task-Aware Agent-driven Prompt Optimization Framework☆3,753Updated 3 months ago
- Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.☆4,909Updated 3 weeks ago
- OctoTools: An agentic framework with extensible tools for complex reasoning☆1,409Updated 3 months ago
- AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/sNGSwQME3x☆4,095Updated this week
- 🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines☆3,693Updated last week
- Tongyi Deep Research, the Leading Open-source Deep Research Agent☆18,165Updated 2 weeks ago
- Tool for generating high quality Synthetic datasets☆1,484Updated 3 months ago
- Build Real-Time Knowledge Graphs for AI Agents☆22,520Updated this week
- "AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"☆8,501Updated 3 months ago
- SOTA search powered LLM☆3,771Updated 10 months ago
- Agent S: an open agentic framework that uses computers like a human☆9,671Updated 2 weeks ago
- The open LLM Ops platform - Traces, Analytics, Evaluations, Datasets and Prompt Optimization ✨☆2,750Updated this week
- About Awesome things towards foundation agents. Papers / Repos / Blogs / ...☆1,955Updated 6 months ago
- Python package and backend for the Elysia platform app.☆1,876Updated this week