hermes-agent
Use the FlashRSI Hermes Snapshot's headless Python runtime, tools, sessions, and compression paths.
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 394
- Forks
- 23
01 前言 Front Matter
- name
- hermes-agent
- license
- MIT
- version
- 1.0.0
- metadata
- { "hermes": { "tags": [ "hermes", "flashrsi", "snapshot", "tools", "sessions", "compression" ], "homepage": "https://github.com/NousResearch/hermes-agent" } }
- platforms
- [ "linux", "macos", "windows" ]
- description
- Use the FlashRSI Hermes Snapshot's headless Python runtime, tools, sessions, and compression paths.
03 SKILL.md 正文
Hermes Agent Snapshot
This Snapshot is the FlashRSI headless Python realization of NousResearch Hermes Agent v0.22.5. It runs the selected Snapshot files directly and keeps the model, API key, endpoint, task directory, and session file in the role or task configuration.
Supported paths
- Chat Completions, OpenAI Responses, and Anthropic Messages over explicit HTTP.
terminal, file, patch, search, todo, skill, and session-search tools.- Multi-turn tool execution, retries, recovery, iteration budgets, output continuation, persistent JSON sessions, and context compression.
- Snapshot-local
SOUL.md,config.yaml, project context files, andskills/.
Use skills_list to find available skills and skill_view to load one. Skill
files are read-only resources; prepare any external commands or credentials in
the task environment before using a skill.
Snapshot boundary
This target does not start the Hermes CLI, Node.js, npm, or a host Hermes profile. The full product's TUI, gateway, desktop, plugins/MCP, cron, delegated agents, provider login/OAuth, and persistent memory service are outside this headless target. Do not infer support for those surfaces from the upstream product documentation; use the Snapshot runtime and role configuration as the source of truth.
04 同仓库更多 Skills
dynamic-resources
Example skill loaded from resources_discover
skill-installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
review-agent
Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.
plugin-creator
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.
openai-docs
Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat/Work/Codex comparisons. Do not use for generic app/software tasks that merely mention Codex.