TokenRhythm releases NeoHorse-1: 4B/9B models post-trained on agent execution traces
rohanpaul_ai · x · 2026-09-17
rohanpaulai highlights a systemic waste: most agent systems throw away their most valuable training data after every run — which model was routed where, which tools were called, what came back, where the agent failed, and how it recovered.
TokenRhythm's NeoHorse-1 (4B/9B family) is post-trained on agent execution traces and outcomes, i.e. on how tasks were actually executed end to end. Technical report, Hugging Face, ModelScope, and GitHub weights are all available as an open release.
More from coding & agent
- One stale date silently broke a WhatsApp reply agent: 19 messages unanswered — petrusenko_max · 2026-11-02
- The 10X engineer is now just a SKILLS.md: 6 workflow rules for AI coding agents — mdancho84 · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- AWS's open-source Strands Harness claims 45% cheaper than Claude Code, reigniting harness debate — blaizedsouza · 2026-11-02
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02