Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

It's a plan
It's a plan
Bifrost
Bifrost
OfinTech Desk
OfinTech Desk
Omnigraph
Omnigraph
Busbar
Busbar

OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

#AI agent#LLM training
Visit GitHub
Python
10.9k
1k
26 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Busbar

Control what AI can do before it acts

Momentum

How fast OpenPipe/ART is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 21 – Nov 20, 2026

Stars +115 in 61 days

0246
6

Forks +39 in 61 days

0123
3

Merged PRs 168 in 61 days

0102030
28

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 21Sep 29Oct 7Oct 15Oct 23Oct 31Nov 8Nov 16
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Mon, Sep 21, 2026+2+11
Tue, Sep 22, 2026+4+13
Wed, Sep 23, 2026+3+24
Thu, Sep 24, 2026+0+07
Fri, Sep 25, 2026+3+19
Sat, Sep 26, 2026+6+38
Sun, Sep 27, 2026+1+22
Mon, Sep 28, 2026+4+020
Tue, Sep 29, 2026+0+113
Wed, Sep 30, 2026+3+23
Thu, Oct 1, 2026+0+04
Fri, Oct 2, 2026+0+213
Sat, Oct 3, 2026+2+128
Sun, Oct 4, 2026+0+00
Mon, Oct 5, 2026+2+11
Tue, Oct 6, 2026+1+00
Wed, Oct 7, 2026+2+00
Thu, Oct 8, 2026+1+11
Fri, Oct 9, 2026+3+10
Sat, Oct 10, 2026+1+09
Sun, Oct 11, 2026+0+10
Mon, Oct 12, 2026+2+01
Tue, Oct 13, 2026+2+00
Wed, Oct 14, 2026+4+20
Thu, Oct 15, 2026+1+00
Fri, Oct 16, 2026+0+00
Sat, Oct 17, 2026+3+10
Sun, Oct 18, 2026+3+20
Mon, Oct 19, 2026+5+12
Tue, Oct 20, 2026+0+02
Wed, Oct 21, 2026+4+13
Thu, Oct 22, 2026+4+13
Fri, Oct 23, 2026+0+10
Sat, Oct 24, 2026+0+10
Sun, Oct 25, 2026+3+00
Mon, Oct 26, 2026+0+13
Tue, Oct 27, 2026+1+00
Wed, Oct 28, 2026+2+10
Thu, Oct 29, 2026+3+00
Fri, Oct 30, 2026+5+00
Sat, Oct 31, 2026+3+00
Sun, Nov 1, 2026+1+00
Mon, Nov 2, 2026+1+10
Tue, Nov 3, 2026+1+00
Wed, Nov 4, 2026+2+26
Thu, Nov 5, 2026+5+01
Fri, Nov 6, 2026+1+03
Sat, Nov 7, 2026+2+15
Sun, Nov 8, 2026+0+10
Mon, Nov 9, 2026+1+10
Tue, Nov 10, 2026+2+02
Wed, Nov 11, 2026+2+10
Thu, Nov 12, 2026+2+00
Fri, Nov 13, 2026+0+00
Sat, Nov 14, 2026+1+08
Sun, Nov 15, 2026+1+02
Mon, Nov 16, 2026+3+01
Tue, Nov 17, 2026+3+00
Wed, Nov 18, 2026+3+00
Thu, Nov 19, 2026+1+00
Fri, Nov 20, 2026+0+00
Total+115+39168
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1
  • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Jul 14 – Aug 27, 2025#1 on 1 day

    #1#5#10#15#20#25
    Top 10
    Aug 2025OctDecFebApr
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about OpenPipe/ART, and every badge it has earned
    1. Aug 221 post
      • I have been fine-tuning LLMs for over 2 years now! Here are the top 12 techniques I'd learn if I were to fine-tune them: Bookmark this. 1. LoRA > Freezes the base weights and trains two low-rank…

        Read full on X, posted by @HeyAnjula

        @HeyAnjula · x.com

    2. 1 month earlier
    3. Jul 141 post
      • 🐍 ART ⭐ 10,471 stars **"Entraînez vos agents IA en quelques clics avec GRPO révolutionnaire !"** 🚀 #GitHub

        Read full on X, posted by @clxymox

        @clxymox · x.com

    4. 21 days earlier
    5. Jun 231 post
      • Shared prefix is the big win, but not the only one. Maxing out packed sequence length and tuning the parallelism setup got us further, up to 35 trajectories/s on 4 GPUs. We published the configs so…

        Read full on X, posted by @wandb

        @wandb · x.com

    6. Jun 202 posts
      • Everyone's celebrating that reward engineering is "solved." The same people who built the solution wrote a post called "Reward Hacking 101." OpenPipe's ART (Agent Reinforcement Trainer) crossed 10K…

        Read full on X, posted by @JayTL00

        @JayTL00 · x.com

      • An open-source Agent Reinforcement Trainer (ART) – plugs GRPO into any Python app → Your app defines the task and reward → ART handles the RL loop: inference, trajectory scoring, GRPO optimization,…

        Read full on X, posted by @TheTuringPost

        @TheTuringPost · x.com

    7. 26 days earlier
    8. May 251 post
      • Your coding agent learns from mistakes on the job. ART gives multi-step agents on-the-job training using GRPO: - Works with Qwen3, GPT-OSS, Llama - W&B serverless RL training - Beat o3 at email…

        Read full on X, posted by @so_sthbryan

        @so_sthbryan · x.com

    9. May 211 post
      • Someone built a framework for training multi-step AI agents on real-world tasks using GRPO and paired it with the first publicly available serverless RL training service. Here's what that actually…

        Read full on X, posted by @RoundtableSpace

        @RoundtableSpace · x.com

    You might also like

    Repositories close to OpenPipe/ART
    FeaturedAdvertise to 180K+ monthly visitors
    Busbar

    Control what AI can do before it acts

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    rllm-org/rllm

    Python

    Democratizing Reinforcement Learning for LLMs

    5.9k653

    KhoomeiK/LlamaGym

    Python

    Fine-tune LLM agents with online reinforcement learning

    1.3k64

    Agent-One-Lab/AgentFly

    Python

    Scalable and extensible reinforcement learning for LM agents.

    12314

    NovaSky-AI/SkyRL

    Python

    SkyRL: A Modular Full-stack RL Library for LLMs

    2.5k497

    modelscope/AgentJet

    Python

    Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.

    24428

    AgentR1/Agent-R1

    Python

    Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

    1.7k147

    areal-project/AReaL

    Python

    The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

    5.9k678

    microsoft/agent-lightning

    Python

    The absolute trainer to light up AI agents.

    19k1.9k

    awslabs/agentcore-rl-toolkit

    Python

    Scalable, Composable Reinforcement Learning for Real-World Agents with Bedrock AgentCore.

    12324