Teknium endorses jumperz's AI agent tier list: Hermes #1, Openclaw slides from S to D
Teknium · x · 2026-10-05
Teknium reposted jumperz's AI agent tier list and backed its #1 pick, open-source Hermes: a hardworking team that fixes issues almost instantly, with model switching, persistent memory, and skills built from past tasks.
Other notables from the list:
- Grok: coordinates longer workflows on its own computer, great UX for newcomers, but usage limits hold it back.
- Muse: persistent cloud VM with a dedicated browser agent and API integrations keeps working after you close it — rated to hit A within months.
- Openclaw: fell from S to D due to inconsistent builds that break after updates; plenty of control but painful to maintain.
More from coding & agent
- AI Swarm hackathon draws hundreds to build monitoring tools after HF and German Wiki incidents — generativist · 2026-10-05
- SPLASH 2026 keynote asks how to keep the engineer in software engineering amid AI coding agents — satnam6502 · 2026-10-05
- GLM vs Qwen tool calling differences force separate handlers in Codex proxy — TheZachMueller · 2026-10-05
- Why running third-party models in Codex needs a tool-calling proxy layer — TheZachMueller · 2026-10-05
- explainroo: a fully local, zero-API pipeline for narrated explainer videos — brandybuckferryman · 2026-10-05
- Dev says nearly all his web searches now run through personal agents as web goes headless — illscience · 2026-10-05