Sato Hub
Agent Framework

Hermes Agent

Open-source self-improving AI agent from Nous Research with a built-in learning loop and one-step migration from OpenClaw.

  • Sato Score92
ActiveVerifiedActive · today

Hermes Agent is an open-source agent framework by Nous Research, with last code activity on 2026-10-23 (Active). Latest release on 2026-10-23. Sato Score 92/100 (how open, active and verifiable it is, not a safety grade), as of 2026-10-24. How the score works →

See how to install Hermes Agent →

Last commit Oct 19, 2026 · Last release Oct 23, 2026 (v0.22.5+canary.20261023T070057Z) · ★ 255,054

Last news post Oct 22, 2026 on X

Listed from hermes-agent.nousresearch.com on 2026-06-08. Install: reproduced by Sato Hub on 2026-09-25. Evidence →

Next step

Watch Hermes Agent

One email if what we observe changes — its repo goes quiet or disappears, or the listing is retired. Nothing else.

Check it from your agent

Add Sato Hub’s MCP server (no key), then ask:

https://satohub.ai/api/mcp
Run Sato Hub Preflight on nousresearch/hermes-agent before I use it.
Full setup: Claude Code, Cursor, others →

Your project?

Prove you control the domain and correct this page — description, links, tags, chains. A claim proves control, not verification: it never changes the Sato Score.

Claim this listing →

Overview

Hermes Agent is an MIT-licensed open-source AI agent from Nous Research, released in February 2026, built around a persistent memory and self-improvement loop that lets it build reusable skills over time. Its setup wizard can automatically detect and migrate an existing OpenClaw installation (settings, memories, skills, API keys). Like OpenClaw it is a general-purpose agent framework rather than a crypto-native tool; onchain use depends on installed skills/MCP servers.

Sato Score

92/100· High

How open, active & verifiable — not a safety or returns grade.

Maintenance & liveness
35/35
Code transparency
20/20
Interface verifiability
8/10
Docs & demo
6/10
Listing transparency & provenance
15/15
Independent verification
8/10

Independently verified — listing reviewed against evidence, never self-reported.

Sato Check

v0.19.0 · as of 2026-09-29
Does it take your key?
No key read found
Does your key leave?
Not yet run
Can it move funds on its own?
Unknown
Full profile, evidence and limits →

A profile describes what we read and ran, with dates. It is not a safety rating, an audit or an endorsement, and "not found" is not "not there".

Evidence — listed vs checked · what the words mean

Listed from hermes-agent.nousresearch.com on 2026-06-08. Install: reproduced by Sato Hub on 2026-09-25.

ClaimValueEvidenceSourceChecked
Chains supportednot statedself-reportedhermes-agent.nousresearch.comas of 2026-10-24
Verification statusVerifiedreview date and evidence link not recorded on this listing✓ reviewed—not dated
Recent activitylast release 2026-10-23 · last commit 2026-10-19observedgithub.com/NousResearch/hermes-agent2026-10-24
Install worksreproduced — install and entry both completedshows the install path works as written; not a statement about runtime behaviour✓ reproducedgithub.com/NousResearch/hermes-agent2026-09-25
Website answersanswered (HTTP 200)observedhermes-agent.nousresearch.com2026-10-24
Daily check record90 of 90 daily checks since 2026-07-26 succeededa success rate of our checks, not uptime; the source is this listing's own historyobserved—2026-10-23
Takes your keyno private-key read found in what we readtracedsatohub.ai2026-09-29
Key leaves the machinenot yet run with planted test keysthe sandbox lane has not run on this versionobservedsatohub.ainot dated
Moves funds on its ownunknown — could not read what it exposestracedsatohub.ai2026-09-29
Built byNous Researchconfidence 0.90self-reportedgithub.com/NousResearch/hermes-agentas of 2026-06-25
Creator profilehttps://github.com/NousResearchconfidence 0.85self-reportedgithub.com/NousResearch/hermes-agentas of 2026-06-25
Deploys asSelf-hosted, Dockerconfidence 0.85self-reportedgithub.com/NousResearch/hermes-agentas of 2026-06-25
Works withTelegram, Discord, Slack, WhatsApp, Signal, MCP, OpenRouter, OpenAIconfidence 0.85self-reportedgithub.com/NousResearch/hermes-agentas of 2026-06-25
Sato Score92/100 (High)how open, active and verifiable — not a safety or quality gradecomputedsatohub.ai2026-10-24

Self-reported rows are the project’s own words, dated when we recorded them — not a check. Only reproduced and reviewed rows carry a mark. None of these rows is a safety or quality rating.

Install — reproduced in a container Sep 25, 2026

Runtime: Python

pip install hermes-agent   # PyPI (Python 3.11–3.13)
# or the official installer / Hermes Desktop app — see docs
hermes setup   # pick a provider: Nous Portal (zero-key OAuth) or bring your own key
hermes         # start a chat

You supply: An LLM provider — Nous Portal (zero-key OAuth) OR a provider API key (ANTHROPIC_API_KEY / OPENROUTER_API_KEY / OPENAI_API_KEY / etc.), A model with a >=64K context window

Read from the project’s own docs as of 2026-09-25. What a deploy spec is →

Observed record — 91 daily checks since 2026-07-26

100%of 91 checks since 2026-07-26 succeeded
Currently responding for 91 days
Succeeded
91
Failed
0
Their error
0
Unattributed
0

This is the share of our daily checks that succeeded — not an availability guarantee. A check can fail because the host was down, because our runner timed out, or because the network in between dropped it, and only the first of those is a fact about this project. Failures are split by what we can attribute; anything we cannot attribute is counted, not hidden. 37 of these checks predate 2026-09-01, when the probe counted a bot-block (HTTP 403) as a failure and recorded no reason for any failure. Every one of them passed, so the rate covers them too.

Last 30 days — to 2026-10-24, one point per UTC day

Share of OUR checks that succeeded
100%
7-day rolling; unattributable days are gaps · 30/30 days
Tools listed
fewer than 2 points—
from the server's own tools/list · 0/30 days
Sato Score
92
as snapshotted that day · 29/30 days

A gap is a day we have no attributable observation — never a zero. Thirty points is the whole shape the free layer carries; the daily rows behind it stay in the snapshot series.

Skills that target this — 1, with disclosures

evmskills.sh · nousresearch

14 installs

"Read-only EVM client: wallets, tokens, gas across 8 chains."

no disclosure flags from the static scan

Disclosures describe what a skill declares and does; they are not safety verdicts. All skills →

Details

Chains
Unknown
Agent types
Personal Assistant, Agent Framework, Self-improving
Open source
Yes
Pricing
Free / self-hosted (open source, MIT)
Deploys as
Self-hosted, Docker
Works with
Telegram, Discord, Slack, WhatsApp, Signal, MCP, OpenRouter, OpenAI
Last checked
2026-10-24

Marketplace Signals

  • ▸ Functional agent

Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.

#agent-framework#open-source#self-improving#nous-research#memory#openclaw-migration#agent-harness
See something inaccurate or outdated?Submit a correction →

Recent Activity

All news →

Releases and posts from Hermes Agent, pulled from its GitHub and X.

ReleaseNousResearch/hermes-agent23h ago

hermes-agent v0.22.5+canary.20261023T070057Z

Hermes Agent canary 20261023T070057Z

GitHub ↗
ReleaseNousResearch/hermes-agent1d ago

hermes-agent Hermes Agent v0.22.5

Hermes Agent v0.22.5 Release Date: October 22, 2026 Patch release. This tag rolls up the ~81 PRs merged since v0.22.4 into a stable release for the GitHub release (CLI and installers), the Microsoft Store app, Docker and Hermes Cloud. Full curated notes for this window ship with v0.23.0. About this release Measured at commit bf0203a794a , the window since v0.22.4 contains 231 non-merge commits acr

GitHub ↗
ReleaseNousResearch/hermes-agent1d ago

hermes-agent rc.3-v0.22.5

{"attempt":3,"autopublish":false,"claimEpoch":1792722320,"commit":"bf…

GitHub ↗
ReleaseNousResearch/hermes-agent1d ago

hermes-agent rc.2-v0.22.5

{"attempt":2,"autopublish":false,"claimEpoch":1792716569,"commit":"a4…

GitHub ↗
Post@NousResearch2d ago

Hermes Agent now has an official plugin for @MeshyAI. Ask Hermes to make a 70m poly treasure chest for Godot, or to turn a photo of a mug into a model you can print, and it does the job through Meshy'

Hermes Agent now has an official plugin for @MeshyAI. Ask Hermes to make a 70m poly treasure chest for Godot, or to turn a photo of a mug into a model you can print, and it does the job through Meshy's MCP server. In Hermes Desktop the models render in chat, rigged characters animate inline, and a gallery stores every model and prompt. On messaging apps, Hermes sends a short preview video so you c

♥ 3661 ↗
Post@NousResearch2d ago

Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale. He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and se

Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale. He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and set up a customized Hermes in one prompt. Then he used Hermes, running on @nvidia RTX Spark, to create a simulated training environment for the @huggingface Microduck. Hermes planned an obstacle course

♥ 11266 ↗

Listing History

Recorded changes to Hermes Agent's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.

  1. Oct 23, 2026
    New release published
  2. Oct 21, 2026
    New release published
  3. Sep 25, 2026
    Verified: deploy spec
  4. Jul 30, 2026
    37 releases tracked
    Showing the 2 most recent. Full release history is retained in the listing record.
  5. Jul 27, 2026
    Sato Hub began tracking this listing
  6. Jun 25, 2026
    Enriched: has pricing, pricing url, marketplace notes
  7. Jun 25, 2026
    Auto-enriched: creator name, creator profile url, supported integrations, deployment options

Compared with

Appears in

Related Resources

Reference

QuestionsShowHide

Questions people ask about Hermes Agent

Is Hermes Agent open source?
Yes. Hermes Agent is open source under the MIT license; the repository is https://github.com/NousResearch/hermes-agent. Checked as of 2026-10-24.
Which chains does Hermes Agent support?
Sato Hub has no confirmed chain list for Hermes Agent as of 2026-10-24; treat chain support as unknown.
Is Hermes Agent still maintained?
The most recent code activity Sato Hub observed was on 2026-10-23 (last commit 2026-10-19, last release 2026-10-23), which Sato Hub labels "Active". Posts on X are not counted as maintenance. Activity is a recency signal, not a quality judgment.
How do I install or run Hermes Agent?
Python. Install: pip install hermes-agent # PyPI (Python 3.11–3.13) && # or the official installer / Hermes Desktop app — see docs. Entry: hermes setup # pick a provider: Nous Portal (zero-key OAuth) or bring your own key hermes # start a chat. Sato Hub reproduced this install in a container on 2026-09-25.
Is Hermes Agent verified on Sato Hub?
Sato Hub holds one earned check for Hermes Agent: Independently verified — listing reviewed against evidence, never self-reported. Its Sato Score is 92 of 100, a measure of how open, active and verifiable the project is, not a safety, quality or returns grade.
Cite this pageShowHide

Cite this page

Sato Hub. "Hermes Agent — Sato Hub." Sato Hub, updated 2026-10-24, accessed 2026-10-24. https://satohub.ai/resources/hermes-agent

Data last refreshed 2026-10-24; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.

Join the Sato Hub Briefing

Sign up for the Briefing: the agents, tools, and infrastructure that actually shipped, and why they matter.