NousResearch / hermes-agent
Hermes Agent ☤
Hermes Agent ☤ The self-improving AI agent built by Nous Research. It’s the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions.
Hermes Agent ☤ 是由 Nous Research 构建的自进化 AI 智能体。它是唯一内置学习循环的智能体——它能从经验中创造技能,在使用过程中不断改进,通过自我提示来固化知识,搜索过往对话,并随着会话深入构建对用户画像的深度理解。
Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It’s not tied to your laptop — talk to it from Telegram while it works on a cloud VM. Use any model you want — Nous Portal, OpenRouter (200+ models), NovitaAI (AI-native cloud for Model API, Agent Sandbox, and GPU Cloud), NVIDIA NIM (Nemotron), Xiaomi MiMo, z.ai/GLM, Kimi/Moonshot, MiniMax, Hugging Face, OpenAI, or your own endpoint. Switch with hermes model — no code changes, no lock-in.
你可以在 5 美元的 VPS、GPU 集群或闲置时几乎零成本的无服务器架构上运行它。它不绑定于你的笔记本电脑——当它在云端虚拟机工作时,你可以通过 Telegram 与它交流。你可以使用任何你想要的模型——Nous Portal、OpenRouter(200+ 模型)、NovitaAI(用于模型 API、智能体沙箱和 GPU 云的 AI 原生云)、NVIDIA NIM (Nemotron)、小米 MiMo、z.ai/GLM、Kimi/Moonshot、MiniMax、Hugging Face、OpenAI 或你自己的端点。通过 hermes model 命令即可切换——无需修改代码,无厂商锁定。
A real terminal interface: Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.
真正的终端界面:完整的 TUI(终端用户界面),支持多行编辑、斜杠命令自动补全、对话历史记录、中断与重定向以及流式工具输出。
Lives where you do: Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity.
随处可用:Telegram、Discord、Slack、WhatsApp、Signal 和 CLI——所有这些都通过单一网关进程实现。支持语音备忘录转录,并保持跨平台的对话连续性。
A closed learning loop: Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall. Honcho dialectic user modeling. Compatible with the agentskills.io open standard.
闭环学习:由智能体管理的记忆,并带有周期性的自我提示。在完成复杂任务后自动创建技能。技能在使用过程中自我优化。支持 FTS5 会话搜索,并结合 LLM 摘要实现跨会话回溯。采用 Honcho 辩证用户建模。兼容 agentskills.io 开放标准。
Scheduled automations: Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.
定时自动化:内置 cron 调度器,可向任何平台发送任务。日报、夜间备份、周度审计——全部以自然语言编写,无需人工干预即可运行。
Delegates and parallelizes: Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.
任务委派与并行处理:生成独立的子智能体以处理并行工作流。编写通过 RPC 调用工具的 Python 脚本,将多步流水线压缩为零上下文成本的交互。
Runs anywhere, not just your laptop: Six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona. Daytona and Modal offer serverless persistence — your agent’s environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster.
不仅限于笔记本电脑,随处可运行:支持六种终端后端——本地、Docker、SSH、Singularity、Modal 和 Daytona。Daytona 和 Modal 提供无服务器持久化——你的智能体环境在闲置时会休眠,按需唤醒,会话间几乎零成本。可在 5 美元的 VPS 或 GPU 集群上运行。
Research-ready: Batch trajectory generation, trajectory compression for training the next generation of tool-calling models.
科研就绪:支持批量轨迹生成,以及用于训练下一代工具调用模型的轨迹压缩。
Quick Install / 快速安装
Linux, macOS, WSL2, Termux
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
Windows (native, PowerShell) Heads up: Native Windows runs Hermes without WSL — CLI, gateway, TUI, and tools all work natively. If you’d rather use WSL2, the Linux/macOS one-liner above works there too. 注意:原生 Windows 可在不使用 WSL 的情况下运行 Hermes——CLI、网关、TUI 和工具均可原生工作。如果你更喜欢使用 WSL2,上述 Linux/macOS 的一行命令同样适用。
iex (irm https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.ps1)
Getting Started / 入门指南
hermes# Interactive CLI — start a conversation / 交互式 CLI — 开始对话hermes model# Choose your LLM provider and model / 选择 LLM 提供商和模型hermes tools# Configure which tools are enabled / 配置启用的工具hermes config set# Set individual config values / 设置单个配置项hermes gateway# Start the messaging gateway (Telegram, Discord, etc.) / 启动消息网关hermes setup# Run the full setup wizard / 运行完整设置向导hermes update# Update to the latest version / 更新至最新版本hermes doctor# Diagnose any issues / 诊断问题
📖 Full documentation → / 完整文档 →
CLI vs Messaging Quick Reference / CLI 与消息平台快速参考
| Action | CLI | Messaging platforms |
|---|---|---|
| Start chatting | hermes | hermes gateway setup + hermes gateway start, then send the bot a message |
| Start fresh conversation | /new or /reset | /new or /reset |
| Change model | /model [provider:model] | /model [provider:model] |
| Set a personality | /personality [name] | /personality [name] |
| Retry or undo | /retry, /undo | /retry, /undo |
| Compress context | /compress, /usage | /compress, /usage |