Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/ART
Library/ARTForked

OpenPipe/ART

ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.5, GPT-OSS, Llama, and more!

View on GitHub↗Upstream OpenPipe/ART↗

Builder

OpenPipe

OpenPipe

OpenPipe • individual

Stars

9,863

Using upstream star count

Forks

876

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Mar 10, 2025

Project creation date

README Summary

<a href="https://art.openpipe.ai"><picture> <img alt="ART logo" src="https://github.com/openpipe/art/raw/main/assets/ART_logo.png" width="160px"> </picture></a>

Community Evaluation

Loading…

AI Dev Skills

Unmapped

Agent-based AI SystemsGroup Relative Policy OptimizationLanguage Model Fine-tuningMulti-step Agent TrainingPolicy Gradient MethodsPolicy OptimizationReinforcement Learning from Human FeedbackReward Model Training

Tags

Agent-based AI SystemsGroup Relative Policy OptimizationLanguage Model Fine-tuningMulti-step Agent TrainingPolicy Gradient MethodsPolicy OptimizationReinforcement Learning from Human FeedbackReward Model TrainingAI AgentsBackendDistillationEvalsForkedGPU / CUDAGRPOGemmaHuggingFaceInferenceJupyterLLM ServingLangGraphLangfuseLarge Language ModelsLoRA / PEFTMCPOpen SourceOpenAIPyTorchPythonQwenReinforcement LearningTRLTorchTuneTransformersUnslothWeights & BiasesvLLM

Taxonomy

AI Trends

Agentic AIReinforcement Learning from Human FeedbackMulti-step ReasoningAI Agent Training

category

Model TrainingFoundation ModelsAI AgentsEvals & BenchmarkingObservability & MonitoringInference & ServingDev Tools & AutomationLearning ResourcesData Science & Analytics

Deployment Context

Self-hosted

Modalities

Text

Skill Areas

Reinforcement Learning from Human FeedbackPolicy Gradient MethodsMulti-step Agent TrainingLanguage Model Fine-tuningGroup Relative Policy OptimizationAgent-based AI SystemsReward Model TrainingPolicy Optimization

tag

AI AgentsBackendDistillationEvalsForkedGPU / CUDAGRPOGemmaHuggingFaceInferenceJupyterLLM ServingLangGraphLangfuseLarge Language ModelsLoRA / PEFTMCPOpen SourceOpenAIPyTorchPythonQwenReinforcement LearningTRLTorchTuneTransformersUnslothWeights & BiasesvLLM

Use Cases

Multi-step Reasoning Task TrainingAgent Behavior OptimizationReal-world Task AutomationComplex Problem Solving Agent Development

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

20

release: Bump version to 0.5.17 (#616)

github-actions[bot] • Mar 13, 2026

4cf171d

feat: Enhance OpenAICompatibleTinkerServer with model management improvements

Brad Hilton • Mar 12, 2026

ca97bff

feat: Add W&B run config API (#615)

Vivek Kalyan • Mar 12, 2026

ca77e97

Quality

prototype
Quality
medium
Maturity
prototype

Categories

Evals & BenchmarkingPrimaryObservability & MonitoringInference & ServingDev Tools & AutomationLearning ResourcesData Science & AnalyticsFoundation ModelsAI AgentsModel TrainingSafety & AlignmentOther AI / ML

PM Skills

Cost & EfficiencyData & EvaluationDeveloper PlatformAI-Native Architecture

Languages

Python100.0%

Timeline

Project created
Mar 10, 2025
Forked
Mar 12, 2026
Your last push
2 months ago
Upstream last push
18 days ago
Tracked since
Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…