Hermes can be used with the DeepSeek V4 Pro model

[windsheep@infosec.exchange]

Hermes can be used with the DeepSeek V4 Pro model

If you set a /goal, it will come up with a multi agent strategy to look for solutions similar to Karpathy's /autoresearch

TUI | Hermes Agent

Launch the modern terminal UI for Hermes — mouse-friendly, rich overlays, and non-blocking input.

(hermes-agent.nousresearch.com)

Persistent Goals | Hermes Agent

Set a standing goal and let Hermes keep working across turns until it's done. Our take on the Ralph loop.

(hermes-agent.nousresearch.com)

I think for coding you are better off with AntiGravity (or claude).

But for RnD or data science, things that require a hypothesis, this is cool.

#hermes #deepseek #research #autoresearch #karpathy

[windsheep@infosec.exchange]

RL Training | Hermes Agent

Reinforcement learning on agent behaviors with Tinker-Atropos — environment discovery, training, and evaluation

(hermes-agent.nousresearch.com)

Hermes is an evolutionary approach. Compared the DSPy agent model, which is programmatic / declarative.

DSPy for many of the use cases, is a lot of work (fine-tuning, debugging). DSPy excels at finance tasks or data analytics where you know all the details. But that is phase 2. Phase 1 is getting these details, and getting them fast. That is imho where Hermes comes in.

I can see myself using Hermes for

* Content tooling: auto-briefing, strategic foresight assessments.
* Intelligence analysis: method approaches to trend analysis or signals
* Individualization of content. OSINT, social media scraping, trend analysis.
* Data sensing, estimation on datasets, start simple
* Autoresearch (later), for example, for optimization solutions or performance debugging

#dspy #hermes #declarative #evolutionary #ai