AI product Open source
Hermes Agent is a self-improving AI agent developed by Nous Research. It provides a CLI and terminal interface, messaging gateway, and desktop interface for interacting with language models, operating terminals and browsers, and maintaining continuity across sessions. It supports model providers including Nous Portal, OpenRouter, OpenAI, and custom endpoints, along with terminal backends including local execution, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox.
Its learning loop creates and improves skills from task experience, stores persistent memories, searches previous sessions with FTS5 and LLM summarization, and builds user profiles through Honcho. It can delegate parallel work to isolated subagents, run Python tool-calling scripts through RPC, schedule unattended jobs with a natural-language cron scheduler, and deliver results through Telegram, Discord, Slack, WhatsApp, Signal, email, and the CLI. The terminal interface includes multiline editing, slash-command completion, conversation history, interrupt-and-redirect controls, and streaming tool output. It also supports voice-memo transcription and cross-platform conversation continuity.
5 uses taken from transcripts — each links to the moment in the video.
Agent harness used with GBrain for the personal AI system.
AI agent framework used for competitor analysis, coding, marketing, growth, customer support, analytics work, and specialized company agents.
Was identified as an agent that could be used for token-maxing and loading very large contexts into a request.
AI agent hosted on a virtual private server to track emails, record invoices, receipts, and transactions, and upload them to an accounting dashboard.
A self-improving personal AI agent that runs through a CLI, TUI, desktop app, and messaging gateway. It learns from experience, persists knowledge, delegates to sub-agents, schedules jobs, and operates terminals and browsers.
6 in the library.