Hermes Agent’s memory and skill stack matter more than the base model, Nous co-founder says
petergyang · x · 2026-08-04
A thread sharing six takeaways from a conversation with Nous Research co-founder Karan about getting more from Hermes Agent.
Key ideas
- The “personal” part of a personal agent is mostly its memory of your conversations and the skills you build on top of it, not the base model itself.
- Karan recommends trying different personas with /personality, such as teacher, concise, kawaii, or pirate.
- He also suggests separating agents that do the work from agents that evaluate it, to avoid reward hacking and make outputs more reliable.
The post argues that model swapping matters less once the agent has strong context and a useful skill set around it.
More from coding & agent
- Long-context voice agents ditch turn detection with async compaction handoff — juberti · 2026-08-04
- Phone-installable PWAs become custom AI agents with Tailscale and Codex — johnlindquist · 2026-08-04
- DeepSeek V4 Flash tops its price tier on GBench and looks much smarter in one-shot tasks — teortaxesTex · 2026-08-04
- Agent DevTools debugs memory, retrieval, and tool calls in local runs — No_Firefighter8428 · 2026-08-04
- Codex edited a full three-camera episode end to end in under 3 hours — danshipper · 2026-08-04
- CTO says an engineer automated 60% of his job with an AI agent and got promoted — sloppenheimer · 2026-08-04