The Hermes Agent Platform is an open-source AI agent framework built by Nous Research. It lets you deploy autonomous AI agents across CLI, messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 10+ more), and IDE environments — all from the same codebase, with the same agent logic, and the same persistent memory.
Runs on Telegram, Discord, Slack, WhatsApp, web, CLI, and TUI from the same agent logic — with full tool access on every platform.
Works with Solar, Claude, GPT, DeepSeek, local Ollama models, and 15+ other providers. No lock-in.
Pluggable memory backends let agents remember across sessions and improve over time.
Agents learn by saving reusable procedures as skills. Skills travel across the fleet and across use cases.
Delegation, subagent spawning, and task routing between independent agent instances with isolated contexts.
Autonomous execution without human polling. The fleet runs on its own cadence.
Agents call APIs, run code, read files. Not just chat.
Run multiple independent Hermes instances with isolated configs, sessions, skills, and memory.