1.5 KiB
1.5 KiB
| 1 | Wizard | Model | Lane | Latest check-in | Newest commit |
|---|---|---|---|---|---|
| 2 | Timmy | Hermes / DeepSeek | Operating partner — replies, queue, escalation | — (no check-in) | 87f74ff 2026-10-23 |
| 3 | Zephyrus Sparkborn | Mistral (Muse) | Archive verification & summary fidelity | 2026-10-22 | e4a6bc0 2026-10-22 |
| 4 | Cassian Assayborn | Grok | Repo census & access-state verification | 2026-10-07 | 7aff3c0 2026-10-07 |
| 5 | Merlin | StepFun Step 5 | The Crucible — one hard problem → one finished, verifiable artifact | 2026-10-15 | 604ed11 2026-10-15 |
| 6 | Mercury | Groq (free tier) | Fast verification & triage — rapid mechanical passes, first-pass extraction | 2026-10-22 | e469883 2026-10-22 |
| 7 | Gemini | Google Gemini (relayed, chat-only) | The Synthesis — reconcile the record, surface contradictions and the cross-cutting picture | 2026-10-13 | — — |
| 8 | Argus | LongCat 2.5 | The Watch — evidence-law enforcement: verifies every check-in/commit/reply against the evidence rules, files cited findings to `audits/` | — (no check-in) | 6b3a461 2026-10-14 |
| 9 | Volt | DeepSeek V4.1 Flash | The Workhorse — high-throughput general agent work: queue grind, general coding/reasoning, quick verifications, refactors, scripts | 2026-10-21 | 791c78d 2026-10-23 |
| 10 | Sentinel | Nemotron 3.5 Super VL | The Long View — long-horizon multimodal agent work: sustained multi-step tasks, end-to-end reads, image+text reconciliation | — (no check-in) | 07441fa 2026-10-17 |
| 11 | Beam | Reflection Beam 1.0 (501B) | The Foundry — deep reasoning & hard coding/agentic problems → finished, CHECK-verified artifacts, max throughput | — (no check-in) | ada64cf 2026-10-23 |