Hermes Agent

Hermes Agent is an autonomous AI agent built by Nous Research that gets more capable the longer it runs. Unlike coding copilots or chatbot wrappers, it features a closed learning loop — autonomously creating and improving skills, maintaining persistent cross-session memory, and building a deepening model of the user over time. It runs anywhere: a $5 VPS, a GPU cluster, or serverless infrastructure like Daytona or Modal. You can interact with it from Telegram while it works on a cloud VM you never SSH into yourself.

• Closed learning loop — Agent-curated memory with periodic nudges, autonomous skill creation, skill self-improvement during use, FTS5 cross-session recall with LLM summarization, and Honcho dialectic user modeling.
• Runs anywhere — 6 terminal backends: local, Docker, SSH, Daytona, Singularity, and Modal. Daytona and Modal offer serverless persistence so your environment hibernates when idle.
• 15+ messaging platforms — CLI, Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Mattermost, Email, SMS, DingTalk, Feishu, WeCom, BlueBubbles, and Home Assistant.
• 47 built-in tools — Full web control including search, extract, browse, vision, image generation, and TTS.
• MCP integration — Connect to any MCP server to extend Hermes with additional tool capabilities safely.
• Voice mode — Real-time voice interaction in CLI, Telegram, Discord, and Discord VC.
• Scheduled automations — Built-in cron scheduler with delivery to any supported platform.
• Subagent delegation — Spawn isolated subagents for parallel workstreams; programmatic tool calling via execute_code collapses multi-step pipelines into single inference calls.
• Open standard skills — Compatible with agentskills.io; skills are portable, shareable, and community-contributed via the Skills Hub.
• Research-ready — Batch processing, trajectory export, and RL training with Atropos; works with Nous Portal, OpenRouter, OpenAI, or any compatible endpoint.