NeoHorse

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

TokenRhythm/NeoHorse

View on GitHub ↗

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

NeoHorse grew +1.1% in the last 30 days, ranks 27th of 370 in Training Toolkits, last commit 57 days ago.

Star trajectory

71 days tracked
2026-09-111.7k stars today2026-11-22
Momentum

+1.1% in 30d, above the Training Toolkits median of +0.3%.

Maintenance

Last commit 57 days ago, fresher than the median of 199.5d.

How it compares in Training Toolkits

NeoHorse
1.7k
stars
+1.1% 30d
commit 57 days ago
Training Toolkits median
320
stars
+0.3% 30d
commit ~199.5d ago
Leader · TTS
46.3k
stars
+0.3% 30d
commit 827 days ago

Ranked 27th of 370 by stars.

Ranked by shared tags, then keywords, then stars

Where NeoHorse sits

Hover or focus a node for details. Click to open it.

  • This repo
  • Related repo
  • Tag or category
  1. Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse…

    +25 (+0.9%) in 30d · Committed 24d ago · Python · MIT

    Shares Reinforcement Learning / RLHF, Training Toolkits

  2. AdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories

    +2 (+0.5%) in 30d · Committed 90d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  3. Official Repo of "RobustFlow: Towards Robust Agentic Workflow Generation"

    +1 (+0.4%) in 30d · Committed 398d ago · Python

    Shares Training Toolkits, Reinforcement Learning / RLHF

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

    +21 (+1.2%) in 30d · Committed 5d ago · Python · MIT

    Shares Reinforcement Learning / RLHF, Training Toolkits

  5. Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool…

    +1k (+205%) in 30d · Committed 2d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  6. A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

    +193 (+16%) in 30d · Committed today · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  7. 🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B…

    +1 (+0.1%) in 30d · Committed 159d ago · Python · Apache-2.0

    Shares Training Toolkits, Reinforcement Learning / RLHF

  8. Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making…

    +14 (+1.6%) in 30d · Committed 279d ago · Python · MIT

    Shares Reinforcement Learning / RLHF, Training Toolkits

  9. Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

    +7 (+1.0%) in 30d · Committed 43d ago · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

  10. An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

    +27 (+4.1%) in 30d · Committed today · Python · Apache-2.0

    Shares Reinforcement Learning / RLHF, Training Toolkits

Language
Python
License
Apache License 2.0
Contributors
6
Forks
26
Watchers
3
Open issues
2
Releases
0
Created
2026-09-04
Stars this week
+5

You've seen where NeoHorse stands today.

Get the moves before everyone else: the 5 Training Toolkits repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain NeoHorse?

Claim this page to add your own call-to-action.

Claim this page