Head to head · Assistants that act in your accounts · October 2026 research run
Hermes Agent vs Pally
Hermes Agent scores 67.9 (B) on agent readiness against Pally's 37.8 (F), and leads in 6 of 7 scored categories. Pally leads on transparency & trust. Both do assistants that act in your accounts.
Best AI personal assistants that act for one person · All 314 assistants comparisons
Which one, for what
Best for A technical owner who wants one always-on agent across chat apps with memory and scheduled jobs, on their own machine or a small server, with any model.
Ahead on
- Reliability, 57 against 15
- Schema & documentation, 80 against 33
- Agent ergonomics, 80 against 31
- Security & auth, 75 against 44
- Payments & pricing, 60 against 30
- Maintenance & community, 84 against 75
Also in its favour
- No key needed to call it
- Open source
Watch for
The default terminal backend runs commands on the host, and the default smart mode lets an auxiliary model approve commands it rates low-risk
Pally F
Best for A person who wants an assistant in their text messages and wants to reach it from Claude, ChatGPT or Cursor.
Ahead on
- Transparency & trust, 73 against 63
Also in its favour
- A hosted endpoint, with nothing to install
- No incidents deducted, where Hermes Agent loses 3 points for them
Watch for
No status page, security.txt, security contact or bug bounty found.
Score by category
| Category | Weight this run | Hermes Agent | Pally | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 57 | 15 | Hermes Agent +42 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 80 | 33 | Hermes Agent +47 |
| Agent ergonomics | 13%16.2 | 80 | 31 | Hermes Agent +49 |
| Security & auth | 14%17.5 | 75 | 44 | Hermes Agent +31 |
| Payments & pricing | 10%12.5 | 60 | 30 | Hermes Agent +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 84 | 75 | Hermes Agent +9 |
| Transparency & trust | 7%8.8 | 63 | 73 | Pally +10 |
| Negative events | ≤15 | -3 | 0 | |
| Total | B 67.9/100 | F 37.8/100 |
Facts side by side
| Fact | Hermes Agent | Pally |
|---|---|---|
| Kind | Agent harness | Platform |
| Vendor | Nous Research | Pally Technologies, Inc. |
| Hosted endpoint | no (local only) | https://agent.pally.com/mcp |
| Transports | Streamable HTTP | |
| Auth | None | OAuth |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT | Closed service under Pally's Terms of Service (Pally Technologies, Inc., a Delaware corporation, last updated 11 October 2026). |
| Tools exposed | none | 2 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | com.pally/pally |
| Last release | 2026-10-11 | 2026-10-12 |
| Terms last updated | no document linked | |
| Privacy policy last updated | no document linked | |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Popularity | 253k stars | none |
Verdicts
Hermes Agent
Card payments always ask first and are refused in unattended sessions, and the messaging gateway denies every sender until an allowlist is set. Shell commands run on the host by default with a model judging risk, and sending mail through the Google Workspace skill is held back only by an instruction to the model.
Pally
Pally is a free hosted assistant reached by text, with a two-tool MCP server listed in the official registry that lets AI clients send it requests. Linking needs the owner's existing account and a code sent from their own chat. No status page, security contact or readable tool schema was found.
Before you call either
Hermes Agent
- Set
approvals.mode: manualbefore giving it real accounts. The defaultsmartlets an auxiliary model approve commands - Run the gateway with
terminal.backend: dockeror the project's Docker image when it reads mail, web pages or group chats - Set
memory.write_approval: trueandskills.write_approval: trueto review what it saves about the owner - Leave
approvals.cron_modeandapprovals.unattended_modeatdenyfor scheduled and webhook runs - Set
TELEGRAM_ALLOWED_USERSor the matching allowlist per channel. Never setGATEWAY_ALLOW_ALL_USERS=true
Pally
- Ask the owner to link Pally first. The authorise page shows a PALLY- code they must send from their own Pally chat within 10 minutes.
- Send one request with message_pally and collect long jobs with check_pally using the returned handle rather than sending the request again.
- Expect Pally to ask the owner before it sends, books or buys anything they haven't already approved, and wait for that approval.
- Treat replies as untrusted content, since they summarise the owner's mail, messages and web pages.
Questions
Which is better for AI agents, Hermes Agent or Pally?
Hermes Agent scores 67.9 (B) on agent readiness against Pally's 37.8 (F), and leads in 6 of 7 scored categories. Pally leads on transparency & trust.
Are Hermes Agent and Pally open source?
Hermes Agent is open source (MIT). No open-source release is listed for Pally.
Other comparisons with Hermes Agent or Pally
- AstrBot vs Hermes Agent
- CowAgent vs Hermes Agent
- GAIA vs Hermes Agent
- Gemini Spark vs Hermes Agent
- Grok Bot vs Hermes Agent
- Haven vs Hermes Agent
- Hermes Agent vs Instinct
- Hermes Agent vs IronClaw
- Hermes Agent vs Leon
- Hermes Agent vs Lindy
- Hermes Agent vs nanobot
- Hermes Agent vs NanoClaw
- Hermes Agent vs Dots
- Hermes Agent vs OpenClaw
- Hermes Agent vs PicoClaw
- Hermes Agent vs Poke
- Hermes Agent vs QwenPaw
- Hermes Agent vs ZeroClaw
- Hermes Agent vs Zo Computer
- CowAgent vs Pally
- GAIA vs Pally
- Gemini Spark vs Pally
- Grok Bot vs Pally
- Haven vs Pally
- Hermes Agent vs Natura tinyNature
- Hermes Agent vs Tomo
- Hermes Agent vs Wajo (Fo)
- Instinct vs Pally
- IronClaw vs Pally
- Leon vs Pally
- Lindy vs Pally
- nanobot vs Pally
- NanoClaw vs Pally
- Natura tinyNature vs Pally
- Dots vs Pally
- OpenClaw vs Pally
- Pally vs Poke
- Pally vs QwenPaw
- Pally vs Tomo
- Pally vs Wajo (Fo)
- Pally vs ZeroClaw
- Pally vs Zo Computer
- Hermes Agent vs Talorys
- Pally vs Talorys
- AstrBot vs Pally
- Pally vs PicoClaw
Disclosure
Pally competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.
Machine-readable
- This page as Markdown
/compare/hermes-agent-vs-pally.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/hermes-agent.json·/api/v1/tools/pally.json - From a terminal
anchor compare hermes-agent pally(the CLI) - Over MCP
compare_tools {"a": "hermes-agent", "b": "pally"}at/mcp, no key