TODO for AI
vs 
Hermes Agent
By Marcell Havlik, founder of TODO for AI · Updated
Open-source self-improving personal agent from Nous Research: skills it writes itself, memory that persists, reachable from 20+ chat apps. Here is where each one wins, with numbers, and who should pick which.
| Fact | Hermes Agent | TODO for AI |
|---|---|---|
| Interface | Chat apps, CLI, desktop app | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Any provider (BYOK or Nous Portal) | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Open | Edge + CLI public |
| Starts at | Free | Free |
Key takeaways
- Models. Hermes Agent model choice: Any provider (BYOK or Nous Portal). TODO for AI runs any provider, Claude, GPT, Gemini, Grok or a local Ollama model, on one plan, and one model can review another's work.
- Benchmark. TODO for AI scored 89.9% on Terminal-Bench 2.1 with Opus 5.5 (high) (own harness, 80/89 tasks, 2026-10-08; not an official leaderboard submission).
- Price. Hermes Agent pricing: MIT, self-hosted, pay providers per token. Nous Portal sells pooled credit plans at roughly $20, $100 and $200 a month; check their site for current credits. TODO for AI has a free plan (Claude Sonnet only), then Starter $20, Pro $100 or Ultra $200 a month with any provider included.
- Where the work happens. Hermes Agent gets one task done on the box you host. TODO for AI is one board your team and agents work through together, on your own PC, a cloud VM and your logged-in Chrome.
- Who should pick which. Pick Hermes Agent if you want MIT source and will host it on your own box or VPS. Pick TODO for AI if you want a list the agent works through, not a chat you scroll.
Hermes Agent
Any provider (BYOK or Nous Portal)
TODO for AI
Any providerWe are not competing for the same job
Hermes Agent gets the task done.
TODO for AI organises the whole company’s work.
Hermes Agent answers one question: how do I get this task done, on the box you host? So do the others — Cursor inside the editor, Claude Code in one person's session, Lindy by asking its assistant.
We answer a different one: where does the work live? One board per project, and a project for each part of the company — engineering, marketing, ops, finance, one per client. Your colleagues work on it. So do your agents, as many as you want to run, each with its own model, tools and permissions. Items carry the people who worked them and the agent that ran them, and the board filters by person, so what the company has in flight is one screen instead of a Slack thread.
That is not a team plan bolted onto an AI tool. It is the product. The agents are how items get closed; the board is what the company runs on.
What Hermes Agent is, and where it stops
Hermes Agent is Nous Research's open-source personal agent and the current centre of gravity for the self-hosted crowd. It is MIT licensed, runs on a $5 VPS or your laptop, and talks to you from Telegram, Discord, Slack, WhatsApp, Signal, email or the terminal. What sets it apart is the learning loop: it writes skills from tasks it has done, refines them on the next run, and keeps a layered memory of you across sessions. A cron scheduler and subagents cover unattended and parallel work, and it can drive a browser. It is positioned as the successor to OpenClaw and imports OpenClaw settings, skills and memories with one command.
The trade is the same as OpenClaw's. You are the operator: install, ports, updates, sandbox choice, and each provider bills you separately unless you buy Nous Portal credits. There is no hosted machine, so it is only as always-on as the box you keep running; browsers are local or a third-party cloud provider you set up. Work lives in chat threads and cron jobs rather than a list, so there is no board of what is open, done or waiting on you.
Technical users who want a self-hosted agent that learns them over time and lives in Telegram, Discord or the terminal.
Three reasons Hermes Agent users look elsewhere
Gateway, sandboxing, updates and key management are yours, on a machine you keep up. The install is one line; the operating is not.
Tasks are messages in a chat plus cron entries. There is no board of what is queued, running, blocked on you or finished, and nothing proposes the next one.
It can attach to a real Chrome profile over CDP or use a cloud browser provider, once you configure them. TODO for AI ships the extension and a cloud browser per account.
Six dimensions that decide it
Hermes Agent 20/30TODO for AI 29/30How does Hermes Agent compare to TODO for AI, feature by feature?
| Feature | Hermes Agent | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | Self-hosted only | Yes |
Model choice | Any (BYOK / Portal) | Any provider |
Cross-vendor review Review GPT output with Claude, or the other way around. | No | Yes |
Drives your real browser Browser extension (Chrome, Firefox) plus cloud browsers. | CDP / real profile, self-configured | Yes |
Business tasks, not only code SEO, email, ads, social, CRM via CLI tools. | Yes | Yes |
Any CLI as an integration | Skills + MCP | Any binary |
Voice control | TTS/STT built in | Yes |
People and agents on one board Colleagues and agents work the same list. Items show who contributed and which agent ran them; filter the board by person. | No | Yes |
Many agents, each configured Each agent gets its own model, prompt, tools and permissions. Pick which one takes an item. | Personas + skills | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | No | Unlimited, shared |
Team roles, pooled usage | Shared gateway, no roles | Roles + pooled |
Tool permissions | Command approvals | Allow, approve, block |
Open runtime | Yes | Edge + CLI public |
Same ladder, different meter
Portal plans are credit pools across 200+ models; tier prices not verified by us. Self-hosted is per-token per provider.
One pool priced in dollars of model cost, spendable on any vendor. Session and weekly windows pace it, and a 1.3-1.5x plan multiplier applies, so a $20 plan is about $15 of list-price API. Team seat prices go into one shared pool.