head to head · open source
Hermes Agent vs Pearl
Hermes Agent has 259,804 GitHub stars, 57,202 forks, 41,784 open issues and last shipped yesterday. Pearl has 1,097 stars, 181 forks, 40 open issues and last shipped 6 months ago. Hermes Agent leads on adoption by 23,583% (259,804 vs 1,097 stars). Hermes Agent is written in Python under MIT; Pearl is written in TypeScript under Apache-2.0. Hermes Agent has attracted 22% as many forks as stars, Pearl 16%. 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, ai-agents), 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.
← all 20902 open source comparisons
Side by side
| Hermes Agent | Pearl | |
|---|---|---|
| GitHub stars | ★ 260K | ★ 1.1K |
| License | MIT | Apache-2.0 |
| Written in | Python | TypeScript |
| Last push | 2026-11-02 | 2026-04-30 |
| Forks | ⑂ 57K | ⑂ 181 |
| 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
pick Pearl if
- You want the Pearl feature set and don't need the biggest community
- You prefer the Apache-2.0 license terms
- Your stack matches TypeScript
- You evaluated both and Pearl fits your workflow better
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 Pearl
Bubble Lab Open core workflow engine powering Bubble Lab — and fully runnable, hostable, and extensible on its own. Use Bubble Lab Platform • View Demos • Documentation Editing Workflows Running Workflows 📋 Overview Bubble Lab is a Slack native AI operator platform that helps teams automate operational work directly inside Slack using Pearl, its AI assistant. Instead of switching between tools, teams can ask Pearl to execute workflows, access systems, and perform tasks across their stack. This repository contains the open core workflow engine that powers the Bubble Lab platform . It is the same execution engine…
read the full Pearl 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 Pearl more popular?
Hermes Agent has 259,804 GitHub stars and Pearl has 1,097. Hermes Agent has the larger community by that measure.
Are Hermes Agent and Pearl free?
Both are open source. Hermes Agent is licensed under MIT and Pearl under Apache-2.0. Neither carries a licence fee.
What is the difference between Hermes Agent and Pearl?
Hermes Agent is written in Python and Pearl 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 Pearl?
Choose Hermes Agent if you want the larger community (259,804 stars) or its MIT licence terms. Choose Pearl if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.