rmax.ai
- 4 followers
- Netherlands
- https://rmax.ai
- hello@rmax.ai
Pinned Loading
Repositories
- jevgrep-eval Public
Reproducible benchmark: Codex Luna code localization with native search vs Jevgrep vs BM25 retrieval
- skills Public
- debate-lab Public
Traceable multi-agent deliberation workbench — structured debate with claims, evidence, and auditable synthesis
- ai-papers-routing-benchmark Public
AI Papers Insights routing benchmark: JEV × model choice × selective PDF reading for paper insights (recovered-run evidence from rmax-ai/delegation-queue#79)
- ai-provider-triage-comparison Public
A small, auditable comparison of OpenAI direct, DeepSeek direct (reasoning off), and Vercel AI Gateway Jev on five support-ticket threads.
- skill-lifecycle-lab Public
Research harness studying evaluation-gated evolution of agent skills: generate → evaluate → select → promote.
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…