TokenRhythm / NeoHorse
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Agentic post-training framework. routing-guided curriculum SFT and routing-guided on-policy distillation turn execution trajectories into training signal while preserving execution and harness context.
- Data quality. exact and near-duplicate removal, evaluation decontamination, structural validation, six-dimensional semantic evaluation, and subscene-level Scene/Goal/Outcome labeling.
- Two release sizes. 4B for a lighter local deployment footprint and 9B for higher capacity on the same text-first serving interface.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 47 days ago
- Stars
- 1,702
- +6 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 33% closed
- 2 still open
- Pull requests
- 1 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| loopx-project / loopx | 6,573 | today | Apache-2.0 | Mac, Windows |
| Tencent-Hunyuan / Hyra-results | 250 | 3 days ago | Custom | No downloads |
| GAIR-NLP / MegaScience | 132 | 4 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Jinja <1%
Topics
- agent
- large-language-models
- llm
- post-training
- recursive-self-improvement
- rsi
Project record
- JobOther AI tools
- StatusListed
- Commits13
- Forks25
- Watching3
- Stars in 28 days+27
- CreatedSep 4, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026