head to head · open source

Hermes Agent vs mercury-agent

Hermes Agent has 259,804 GitHub stars, 57,202 forks, 41,784 open issues and last shipped yesterday. mercury-agent has 3,768 stars, 388 forks, 60 open issues and last shipped yesterday. Hermes Agent leads on adoption by 6,795% (259,804 vs 3,768 stars). Hermes Agent is written in Python under MIT; mercury-agent is written in TypeScript under MIT. Hermes Agent has attracted 22% as many forks as stars, mercury-agent 10%. Hermes Agent was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (ai-agent, llm), so they are genuine substitutes rather than adjacent tools.

Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.

Hermes Agent ★ 260K mercury-agent ★ 3.8K category AI & Machine Learning

← all 20902 open source comparisons

Side by side

Hermes Agent mercury-agent
GitHub stars ★ 260K ★ 3.8K
License MIT MIT
Written in Python TypeScript
Last push 2026-11-02 2026-11-02
Forks ⑂ 57K ⑂ 388
Self-hosting Yes Yes
Data ownership Your server Your server

pick Hermes Agent if

  • You weight community size — 260K stars and counting
  • You want the MIT license terms
  • Your stack matches Python
  • You value the larger contributor base for long-term maintenance

full Hermes Agent profile →

pick mercury-agent if

  • You want the mercury-agent feature set and don't need the biggest community
  • You prefer the MIT license terms
  • Your stack matches TypeScript
  • You evaluated both and mercury-agent fits your workflow better

full mercury-agent profile →

About Hermes Agent

Hermes Agent ☤ Hermes Agent Hermes Desktop 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. 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, OpenAI, your own endpoint, and many…

read the full Hermes Agent overview →

About mercury-agent

Soul driven AI agent with permission hardened tools, token budgets, and multi channel access. Remembers what matters. Asks before it acts. Runs 24/7 from CLI, Telegram, or Web. 31 built in tools, Kanban boards, extensible skills, SQLite backed Second Brain memory. 🔖 Current Stable: v1.2.3 English 简体中文 Quick Start One liner install (no Node.js required) — downloads the latest standalone binary for your OS: Or via npm if you already have Node.js 20+: Or install the npm package globally: First run triggers the setup wizard (name, provider, optional Telegram). After setup, Mercury opens the Ink TUI startup screen…

read the full mercury-agent overview →

More in AI & Machine Learning

Related comparisons

More AI Interaction & Interfaces projects

Compare either of these against the rest of the AI Interaction & Interfaces field.

Frequently asked questions

Is Hermes Agent or mercury-agent more popular?

Hermes Agent has 259,804 GitHub stars and mercury-agent has 3,768. Hermes Agent has the larger community by that measure.

Are Hermes Agent and mercury-agent free?

Both are open source. Hermes Agent is licensed under MIT and mercury-agent under MIT. Neither carries a licence fee.

What is the difference between Hermes Agent and mercury-agent?

Hermes Agent is written in Python and mercury-agent in TypeScript. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, Hermes Agent or mercury-agent?

Choose Hermes Agent if you want the larger community (259,804 stars) or its MIT licence terms. Choose mercury-agent if its feature set, stack or MIT licence fits better. Both are self-hostable.