Hermes Agent
Open-source self-improving AI agent from Nous Research with a built-in learning loop and one-step migration from OpenClaw.
Last release Jul 20, 2026 · Last commit Jul 18, 2026 · ★ 216,720
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
84/100· HighHow open, active & verifiable — not a safety or returns grade.
- Maintenance & liveness
- 35/35
- Code transparency
- 20/20
- Interface verifiability
- 0/10
- Docs & demo
- 6/10
- Listing transparency & provenance
- 15/15
- Independent verification
- 8/10
Independently verified — listing reviewed against evidence, never self-reported.
Details
- Chains
- Unknown
- Agent types
- Personal Assistant, Agent Framework, Self-improving
- Open source
- Yes
- Pricing
- Free / self-hosted (open source, MIT)
- Last checked
- 2026-07-25
Marketplace Signals
- ▸ Functional agent
Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.
Recent Activity
All news →Releases and posts from Hermes Agent, pulled from its GitHub and X.
New in Hermes Agent: a credential firewall for Docker sandboxes. Your real keys never enter the sandbox. It runs on stand-in tokens, and a local proxy swaps in the real keys at the network boundary. T
New in Hermes Agent: a credential firewall for Docker sandboxes. Your real keys never enter the sandbox. It runs on stand-in tokens, and a local proxy swaps in the real keys at the network boundary. Tokens from a compromised sandbox are useless elsewhere. > hermes egress setup https://t.co/4x3088Jp8v
You're not gonna believe this https://t.co/3KCfbE9SbW https://t.co/8Ejm2Hey5p
Ling-3.0-flash, the new MoE model from @AntLingAGI, is now free in Nous Portal for the next week! At 124B parameters and 5.1B active, it's quick to run and built for agent workloads: coding, search, r
Ling-3.0-flash, the new MoE model from @AntLingAGI, is now free in Nous Portal for the next week! At 124B parameters and 5.1B active, it's quick to run and built for agent workloads: coding, search, research, and tool use. Try it free today at https://t.co/3Uj27KjSik
Hermes now has an optional skill for tldraw offline, @tldraw's desktop whiteboard. It reads your open canvas, edits it live, and can embed a script in the file so the drawing opens with working button
Hermes now has an optional skill for tldraw offline, @tldraw's desktop whiteboard. It reads your open canvas, edits it live, and can embed a script in the file so the drawing opens with working buttons and state. > hermes skills install optional-skills/creative/tldraw-offline https://t.co/3JbJ6KDnG5
All models are now 20% off for a limited time at Nous Portal, the best way to power your Hermes Agent. Yes, even the expensive frontier models. https://t.co/aHGXAcLs93 https://t.co/fJHbC08FtC
The new Laguna S 2.1 model by @poolsideai is now free for 2 weeks on Nous Portal. At 118B total parameters with 8B active, it's quick to run and the most capable model they've released so far. Try Por
The new Laguna S 2.1 model by @poolsideai is now free for 2 weeks on Nous Portal. At 118B total parameters with 8B active, it's quick to run and the most capable model they've released so far. Try Portal today at https://t.co/3Uj27KjSik
Listing History
Recorded changes to Hermes Agent's listing — status, verification, Sato Score, and recent releases. Full history is kept in the listing record.
- Jul 20, 2026New release published
- Jul 8, 2026New release published
- Jun 25, 2026Enriched: has pricing, pricing url, marketplace notes
- Jun 25, 2026Auto-enriched: creator name, creator profile url, supported integrations, deployment options
- Jun 16, 2026Edited: deploy spec
- Jun 16, 20265 releases trackedShowing the 2 most recent. Full release history is retained in the listing record.
- Jun 11, 2026Sato Hub began tracking this listing
Related Resources
ElizaOS
ActiveOpen-source TypeScript framework for building crypto-native multi-agent systems.
Model Context Protocol (MCP)
ActiveAnthropic's open standard for connecting AI systems to external tools and data sources.
Olas (Autonolas)
ActiveNetwork and framework for co-owned autonomous agent services operating onchain.
Join the Sato Hub Briefing
One email a week — the agents, tools, and infrastructure that actually shipped, and why they matter.