Overview
This repository is a personal fork of the open-source NousResearch/hermes-agent project, maintained by a self-described beginner who builds by trial and error with AI agents. The fork adds a local "Model Groups" web panel, a per-run cost ceiling, and a fallback approval gate on top of the upstream agent. The author states that it is an amateur, early-stage personal project where bugs are likely and everything runs on the author's own machine. The upstream Hermes Agent is described as a self-improving AI agent built by Nous Research with a built-in learning loop, a terminal interface, messaging-platform integrations, scheduled automations, subagent delegation, and multiple terminal backends. The fork's installation steps install from source and require Git, Python 3.11, Node.js 18+, and uv. Because the fork diverges from upstream, the hermes update command does not work in this fork; upstream changes must be pulled manually via git remote and merge.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Operators use the per-run cost ceiling to cap a run's spending in USD before the next API call.
- Teams use the fallback approval gate to require explicit approval before escalating to the next model tier.
- Users can pre-authorise a single run with an environment variable instead of approving interactively.
- Users install the fork from source on Linux, macOS, or WSL2 using git clone and uv.
- Users install the fork from source on Windows using PowerShell.
- Maintainers pull upstream changes manually because the fork diverges from upstream.
Features
AI assistant
Natural language interface
Workflow automation
Reviews
No reviews yet. Be the first to share your experience!