Hermes Agent user slams 'endless bugs' in tools and integrations; Nous says he installed a community fork
diggz976 · x · 2026-09-07
A user publicly complained that Nous Research's Hermes Agent works fine until you touch advanced features — tools, gateways, context, integrations — which produce "endless bugs," with fixes that "every 2 days solve one issue and introduce two new ones."
Teknium of Nous Research pushed back, noting the GitHub repo the user linked is a completely independent community project that the official website neither links to nor pulls from, suggesting an install-source mix-up. The exchange highlights how confusing distribution channels can sour open-source agent adoption, and that tool-use reliability remains the weak spot even for agents that demo well.
More from coding & agent
- Open-source Graft fights coding agent amnesia with markdown, claims SWE-bench win over Claude Code — thisdudelikesAI · 2026-09-07
- New Agent Workflow: Have AI Implement a Feature Once to Learn, Then Rebuild From Scratch — remilouf · 2026-09-07
- Founder's real-time AI avatar handled inbound sales during paternity leave, closing prospects — toolstelegraph · 2026-09-07
- Dev mocked as vibe coder claps back: I can write FizzBuzz in under 15 minutes — tlakomy · 2026-09-07
- Running 4 parallel agents feels like babysitting 4 toddlers, dev says — smlpth · 2026-09-07
- My Text Expander Has a Desk: outsourcing Espanso config upkeep to an AI — bfrench · 2026-09-07