Local self-improving agents

Hermes Agent

self-improvement is baked in:
after the task, the agent saves the approach as a reusable "skill" and persists memory across sessions
Integrated with Inference Providers or serve LM locally

# use with inference providers
HF_TOKEN=hf_...
hermes chat --provider hf

# use with local served endpoint
(llama.cpp & friends)
hermes config set OPENAI_BASE_URL
http://localhost:8080/v1
hermes config set OPENAI_API_KEY dummy
hermes config set LLM_MODEL your-model-name

# start chatting
hermes chat