SYLIN

Hermes Agent

by Nous Research · Agent · Text & code

promising

Fahd Mirza reuses it as a test harness for many models; little else is known

New /loop command re-runs a prompt on a recurring timer, re-reading current state each wake-up and reporting back

Why we say so

Fahd Mirza ran it hands-on with Qwen4 Max, Hy4 flash, Maxwell V1.0 Flash, Apex 35B and Gemini 4 Neon, including screen control and sub-agents, and no problems were reported. The only negative is a report from @DanielLenton1 that it failed to memorize or generalize on Continual-ARC, which is a narrow test. One tester supplies nearly all the evidence, and no one has compared it with other agents.

Evidence

  1. Nov 19
    Used as the harness for Hy4 flash, including computer use of the screen with clicking and typing in real apps
  2. Sep 8
    Demo watched a simulated four-stage deploy; loop ended itself after five wake-ups, switching to file mtime checks when reads were deduplicated
  3. Sep 2
    Paired with Qwen 3.8 Flash Next, called the local agentic gold standard by the reviewer for speed
  4. Aug 21
    Commenter says Hermes currently has the upper hand over OpenClaw among people building multi-agent systems
  5. Aug 18
    /loop stops after a fixed count, a natural-language condition, a judge model check, or when the agent decides it is done
Show all 7
  1. Aug 18
    Rule of thumb: /loop for timer-driven watching, /goal for judge-driven fixing, cron for unattended work that outlives the terminal
  2. Aug 1
    With a local Qwen 27B via Ollama, it picked the Obsidian skill and found the vault unprompted for a plain note request

Alternatives

Qwen3.8-9B (Empero)Built a working multi-service Docker crypto tracker (API, frontend, Redis, Nginx) from one agentic prompt; Solana data stayed empty
Ornith 1.5 9BFailed an AWS CLI EC2 provisioning task in Hermes Agent: command errors, typos, 43k tokens in 7 minutes without finishing
Prime AgentInterface is more minimal than Hermes Agent or OpenClaw; reviewer finds that acceptable
GLMIn Hermes Agent it found and fixed a safety-separation bug in a multi-container Docker air-traffic app within about 2 minutes, with no hints