mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-11 13:41:53 +00:00
5e5191b9fa
Adapts Claude Code's research-preview dynamic workflows (plan-in-code fan-out, hundreds of subagents per session) to Hermes invariants. The ported mechanic is plan/loop/intermediate-state-out-of-context, not more subagents. Documents the two real orchestration layers and the hard capability boundary between them: - Layer A (execute_code): deterministic fan-out, SANDBOX_ALLOWED_TOOLS only, cannot call delegate_task - Layer B (delegate_task batch): LLM-judgment fan-out Plus the synchronous trap (delegate_task is turn-scoped, cancelled on new message; durable/resumable = kanban swarm) and the genuinely-new piece: the adversarial-convergence verification recipe (N independent attempts with varied framings + M refuters, keep only located claims that survive refutation, iterate to convergence). Self-contained: inlines the load-bearing fan-out hygiene rather than hard-depending on local-only skills; references the shipped kanban swarm subsystem for the durable path. |
||
|---|---|---|
| .. | ||
| apple | ||
| autonomous-ai-agents | ||
| computer-use | ||
| creative | ||
| data-science | ||
| dogfood | ||
| github | ||
| index-cache | ||
| media | ||
| mlops | ||
| note-taking | ||
| productivity | ||
| research | ||
| smart-home | ||
| social-media | ||
| software-development | ||
| yuanbao | ||