Repository · GitHub
Sheltercosmo/Rilldex-RL-Studio
RL observability for LLM agents: behavior maps, native trainer metrics, rollout investigations, and Python/SQL analysis.
| Owner | Sheltercosmo |
|---|---|
| Stars | 25 |
| Forks | 7 |
| Main language | Python |
| Created | 16 October 2026 |
| Last updated at source | 21 October 2026 |
Stars, last 2 days
25 now (+2 since 2026-10-20). Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 21 Oct 2026 Topics added ai-agents, artificial-intelligence, data-visualization, deep-learning, generative-ai, large-language-models, llm-evaluation, llm-observability, llmops, machine-learning, monitoring, observability, post-training, reward-hacking, rlhf removed agent-observability, behavior-analysis, ppo, rl-observability, rollouts, sqlite, training-monitoring, trl, verl
Changes detected by Silytics between refreshes of the source.
More from Sheltercosmo
- jev4pgRepository
Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.