JH

jacobhausler/hermes-workflows

Developer tools

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

4 stars Качество 62 Тренд 26MIT

Agent-owned workflow graphs for Hermes Agent: nodes, fan-outs, gates, fingerprint-resume, desktop DAG view

Обзор

Your agent authors a JSON graph of agent nodes, fan-outs and gates; a background runner executes it outside the caller process tree and hands results back through the same workflow tool it launched from. Hermes Desktop draws the live DAG. A single agent turn is one long, fragile thread of work: one context, one timeout, no resumable checkpoints. A splits the job into nodes with explicit dependencies — parallel recon lanes, a synthesis join, an adversarial review gate — each node a separate child session with its own model, budget, and typed failure. When something dies or you change your mind mid-flight, only the affected nodes re-run: completed work is replayed from its stored fingerprint, not re-paid. One tool, action-routed — the complete surface, with the flags that matter: Plus a /wf slash command: bare /wf lists the library; /wf [note] launches that graph with the note as its context seed.

README

Показан фрагмент оригинального README. Открыть оригинал.

Hermes Workflows

Agent-owned workflow graphs for Hermes Agent. Your agent authors a JSON graph of agent nodes, fan-outs and gates; a background runner executes it outside the caller process tree and hands results back through the same workflow tool it launched from. Hermes Desktop draws the live DAG.

Four production diagrams, glossed two lines each: docs/showcase.md.

Why this exists

A single agent turn is one long, fragile thread of work: one context, one timeout, no resumable checkpoints. A graph splits the job into nodes with explicit dependencies — parallel recon lanes, a synthesis join, an adversarial review gate — each node a separate child session with its own model, budget, and typed failure. When something dies or you change your mind mid-flight, only the affected nodes re-run: completed work is replayed from its stored fingerprint, not re-paid.

What you get

Capability In one line
Graph runs Agent nodes with goal, after edges, per-node model/provider/reasoning, and max_turns/timeout/run_budget caps; optional concurrency/item_concurrency — per graph or as launch-time run args, clamped to owner caps
Fan-out One node → N live children from fanout.items or items_from:".items"; per-item liveness; quorum cancels stragglers once N commit (they are cancelled, never a failure)
Human + machine gates A gate holds on a question until release; gate.wait holds on a timer or an argv probe at zero token cost; when predicates branch on upstream output; on_skip:"prune" retires the losing arm; an optional default-off admission gate answers human releases at zero turns (docs/admission-gates.md)
Fingerprint resume Crash, restart, or amend the graph mid-flight — nodes whose effective fingerprint still matches replay-skip; only what actually changed re-runs. run/amend accept dry_run:true for a no-write preview
Cooperative steer steer queues text for a running node; the child pulls it at its next natural seam via the tool’s inbox action — prompts are never rewritten mid-flight
Profile delegation A node can run as another local Hermes profile (its instructions, memory, tools) behind a per-profile consent file — multi-personality graphs on one machine, no isolation claimed
Открыть полный README на GitHub

Рекомендуемые инструменты

Попробуйте другой запрос или уберите фильтр.

Установка

npx skillfish add jacobhausler/hermes-workflows
Новичок в MCP? Начните с руководства на mcpskill.org →