Документация Hermes Agent
Полная документация по установке, настройке и использованию Hermes Agent.
Начало работы
Руководство пользователя
- Контрольные точки и откат
- CLI
- Configuration
- Настройка моделей
- Docker
- Git Worktrees
- Профили
- Безопасность
- Сессии
- TUI
- BlueBubbles
- DingTalk
- Discord
- Feishu
- Home Assistant
- Messaging Gateway
- Matrix
- Mattermost
- Open WebUI
- QQ Bot
- Signal
- Slack
- SMS
- Teams
- Telegram
- Webhooks
- WeCom Callback
- WeCom
- Weixin
- Yuanbao
- ACP
- API-сервер
- Пакетная обработка
- Браузер
- Встроенные плагины
- Выполнение кода
- Контекстные файлы
- Контекстные ссылки
- Пулы учетных данных
- Scheduled Tasks (Cron)
- Куратор
- Делегирование
- Расширение панели
- Запасные провайдеры
- Цели
- Honcho
- Хуки
- Генерация изображений
- Kanban: учебник
- Kanban
- MCP
- Провайдеры памяти
- Память
- Обзор
- Личность
- Плагины
- Маршрутизация провайдеров
- RL-обучение
- Навыки
- Скины
- Spotify
- Tool Gateway
- Tools & Toolsets
- TTS
- Vision
- Голосовой режим
- Веб-панель
- G0DM0D3 — Godmode Jailbreaking
- Google Workspace — Gmail, Calendar, Drive, Sheets & Docs
- Blender Mcp — Control Blender directly from Hermes via socket connection to the blender-mcp addon
- Concept Diagrams
- Meme Generation — Generate real meme images by picking a template and overlaying text with Pillow
- Base
- Solana
- Agentmail — Give the agent its own dedicated email inbox via AgentMail
- Fitness Nutrition — Gym workout planner and nutrition tracker
- Neuroskill Bci
- Blackbox — Delegate coding tasks to Blackbox AI CLI agent
- Honcho
- Bioinformatics — Gateway to 400+ bioinformatics skills from bioSkills and ClawBio
- Domain Intel — Passive domain reconnaissance using Python stdlib
- Drug Discovery — Pharmaceutical research assistant for drug discovery workflows
- Duckduckgo Search — Free web search via DuckDuckGo — text, news, images, videos
- Gitnexus Explorer
- Parallel Cli
- Qmd
- Scrapling
- 1Password — Set up and use 1Password CLI (op)
- Oss Forensics — Supply chain investigation, evidence recovery, and forensic analysis for GitHub repositories
- Sherlock — OSINT username search across 400+ social networks
- Canvas — Canvas LMS integration — fetch enrolled courses and assignments using API token authentication
- Here.Now — Publish static sites to {slug}
- Memento Flashcards — Spaced-repetition flashcard system
- Shopify — Shopify Admin & Storefront GraphQL APIs via curl
- Siyuan
- Telephony — Give Hermes phone capabilities without core tool changes
- One Three One Rule — Structured decision-making framework for technical proposals and trade-off analysis
- Inference Sh Cli — Run 150+ AI apps via inference
- Docker Management
- Adversarial Ux Test — Roleplay the most difficult, tech-resistant user for your product
- Huggingface Accelerate — Simplest distributed training API
- Chroma — Open-source embedding database for AI applications
- Clip — OpenAI's model connecting vision and language
- Faiss — Facebook's library for efficient similarity search and clustering of dense vectors
- Optimizing Attention Flash
- Guidance
- Hermes Atropos Environments — Build, test, and debug Hermes Agent RL environments for Atropos training
- Huggingface Tokenizers — Fast tokenizers optimized for research and production
- Instructor
- Lambda Labs Gpu Cloud — Reserved and on-demand GPU cloud instances for ML training and inference
- Llava — Large Language and Vision Assistant
- Modal Serverless Gpu — Serverless GPU cloud platform for running ML workloads
- Nemo Curator — GPU-accelerated data curation for LLM training
- Peft Fine Tuning — Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods
- Pinecone — Managed vector database for production AI applications
- Pytorch Fsdp
- Pytorch Lightning
- Qdrant Vector Search — High-performance vector similarity search engine for RAG and semantic search
- Sparse Autoencoder Training
- Simpo Training — Simple Preference Optimization for LLM alignment
- Slime Rl Training — Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework
- Stable Diffusion Image Generation
- Tensorrt Llm — Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency
- Distributed Llm Pretraining Torchtitan
- Whisper — OpenAI's general-purpose speech recognition model
- Openclaw Migration — Migrate a user's OpenClaw customization footprint into Hermes Agent
- Page Agent
- Fastmcp — Build, test, inspect, install, and deploy MCP servers with FastMCP in Python
- Mcporter
- Obsidian — Read, search, and create notes in the Obsidian vault
- Architecture Diagram — Dark-themed SVG architecture/cloud/infra diagrams as HTML
- Ascii Art — ASCII art: pyfiglet, cowsay, boxes, image-to-ascii
- Ascii Video — ASCII video: convert video/audio to colored ASCII MP4/GIF
- Baoyu Comic — Knowledge comics (知识漫画): educational, biography, tutorial
- Baoyu Infographic — Infographics: 21 layouts x 21 styles (信息图, 可视化)
- Claude Design — Design one-off HTML artifacts (landing, deck, prototype)
- Comfyui
- Ideation — Generate project ideas via creative constraints
- Design Md — Author/validate/export Google's DESIGN
- Excalidraw — Hand-drawn Excalidraw JSON diagrams (arch, flow, seq)
- Humanizer — Humanize text: strip AI-isms and add real voice
- Manim Video — Manim CE animations: 3Blue1Brown math/algo videos
- P5Js — p5
- Pixel Art — Pixel art w/ era palettes (NES, Game Boy, PICO-8)
- Popular Web Designs — 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS
- Pretext
- Sketch — Throwaway HTML mockups: 2-3 design variants to compare
- Songwriting And Ai Music — Songwriting craft and Suno AI music prompts
- Touchdesigner Mcp
- Godmode — Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN
- Debugging Hermes Tui Commands — Debug Hermes TUI slash commands: Python, gateway, Ink UI
- Hermes Agent Skill Authoring — Author in-repo SKILL
- Node Inspect Debugger — Debug Node
- Plan — Plan mode: write markdown plan to
- Python Debugpy — Debug Python: pdb REPL + debugpy remote (DAP)
- Requesting Code Review — Pre-commit review: security scan, quality gates, auto-fix
- Spike — Throwaway experiments to validate an idea before build
- Subagent Driven Development — Execute plans via delegate_task subagents (2-stage review)
- Systematic Debugging — 4-phase root cause debugging: understand bugs before fixing
- Test Driven Development — TDD: enforce RED-GREEN-REFACTOR, tests before code
- Writing Plans — Write implementation plans: bite-sized tasks, paths, code
- Yuanbao — Yuanbao (元宝) groups: @mention users, query info/members
- Codebase Inspection — Inspect codebases w/ pygount: LOC, languages, ratios
- Github Auth — GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login
- Github Code Review — Review PRs: diffs, inline comments via gh or REST
- Github Issues — Create, triage, label, assign GitHub issues via gh or REST
- Github Pr Workflow — GitHub PR lifecycle: branch, commit, open, CI, merge
- Github Repo Management — Clone/create/fork repos; manage remotes, releases
- Gif Search — Search/download GIFs from Tenor via curl + jq
- Heartmula — HeartMuLa: Suno-like song generation from lyrics + tags
- Songsee — Audio spectrograms/features (mel, chroma, MFCC) via CLI
- Spotify — Spotify: play, search, queue, manage playlists and devices
- Youtube Content — YouTube transcripts to summaries, threads, blogs
- Himalaya — Himalaya CLI: IMAP/SMTP email from terminal
- Claude Code — Delegate coding to Claude Code CLI (features, PRs)
- Codex — Delegate coding to OpenAI Codex CLI (features, PRs)
- Hermes Agent — Configure, extend, or contribute to Hermes Agent
- Opencode — Delegate coding to OpenCode CLI (features, PR review)
- Arxiv — Search arXiv papers by keyword, author, category, or ID
- Blogwatcher — Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool
- Llm Wiki — Karpathy's LLM Wiki: build/query interlinked markdown KB
- Polymarket — Query Polymarket: markets, prices, orderbooks, history
- Research Paper Writing — Write ML papers for NeurIPS/ICML/ICLR: design→submit
- Airtable — Airtable REST API via curl
- Google Workspace — Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python
- Linear — Linear: manage issues, projects, teams via GraphQL + curl
- Maps — Geocode, POIs, routes, timezones via OpenStreetMap/OSRM
- Nano Pdf — Edit PDF text/typos/titles via nano-pdf CLI (NL prompts)
- Notion — Notion API via curl: pages, databases, blocks, search
- Ocr And Documents — Extract text from PDFs/scans (pymupdf, marker-pdf)
- Powerpoint — Create, read, edit
- Minecraft Modpack Server — Host modded Minecraft servers (CurseForge, Modrinth)
- Pokemon Player — Play Pokemon via headless emulator + RAM reads
- Xurl — X/Twitter via xurl CLI: post, search, DM, media, v2 API
- Kanban Orchestrator
- Kanban Worker — Pitfalls, examples, and edge cases for Hermes Kanban workers
- Webhook Subscriptions — Webhook subscriptions: event-driven agent runs
- Dogfood — Exploratory QA of web apps: find bugs, evidence, reports
- Evaluating Llms Harness — lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc
- Weights And Biases — W&B: log ML experiments, sweeps, model registry, dashboards
- Huggingface Hub — HuggingFace hf CLI: search/download/upload models, datasets
- Llama Cpp — llama
- Obliteratus — OBLITERATUS: abliterate LLM refusals (diff-in-means)
- Outlines — Outlines: structured JSON/regex/Pydantic LLM generation
- Serving Llms Vllm — vLLM: high-throughput LLM serving, OpenAI API, quantization
- Audiocraft Audio Generation — AudioCraft: MusicGen text-to-music, AudioGen text-to-sound
- Segment Anything Model — SAM: zero-shot image segmentation via points, boxes, masks
- Dspy — DSPy: declarative LM programs, auto-optimize prompts, RAG
- Axolotl — Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO)
- Fine Tuning With Trl — TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF
- Unsloth — Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM
- Jupyter Live Kernel — Iterative Python via live Jupyter kernel (hamelnb)
- Native Mcp — MCP client: connect servers, register tools (stdio/HTTP)
- Openhue — Control Philips Hue lights, scenes, rooms via OpenHue CLI
- Apple Notes — Manage Apple Notes via memo CLI: create, search, edit
- Apple Reminders — Apple Reminders via remindctl: add, list, complete
- Findmy — Track Apple devices/AirTags via FindMy
- Imessage — Send and receive iMessages/SMS via the imsg CLI on macOS
Разработчикам
- Внутренности ACP
- Добавление платформенных адаптеров
- Добавление провайдеров
- Добавление инструментов
- Цикл агента
- Архитектура
- Браузерный супервизор
- Сжатие и кэширование контекста
- Плагин Context Engine
- Участие в разработке
- Создание навыков
- Внутренности Cron
- Окружения
- Расширение CLI
- Внутренности Gateway
- Плагин Memory Provider
- Сборка промпта
- Рантайм провайдера
- Хранилище сессий
- Рантайм инструментов
- Формат траекторий
Гайды
- Automate Anything with Cron
- Шаблоны автоматизации
- AWS Bedrock
- Azure AI Foundry
- Создание плагина Hermes
- Script-Only Cron Jobs (No LLM)
- Диагностика Cron
- Ежедневный дайджест-бот
- Паттерны делегирования
- GitHub PR Review Agent
- Локальная LLM на Mac
- Миграция с OpenClaw
- Minimax OAuth
- Python-библиотека
- Командный Telegram-ассистент
- Советы
- Использование MCP с Hermes
- Использование Soul с Hermes
- Голосовой режим с Hermes
- Webhook GitHub PR Review
- Работа с навыками