gbrain-retrieval-reflex.yaml 950 B

123456789101112131415
  1. name: gbrain-retrieval-reflex
  2. repo: https://github.com/aean0x/hermes-gbrain-retrieval-reflex
  3. sha: 78516ca629588612ebfc0a7ca86944fbb63d7dd8
  4. description: "pre_llm_call hook plugin, enabled with `hermes plugins enable`: injects ambient context from a GBrain instance before each turn (volunteer_context, then a hybrid-query fallback). Not a `memory.provider`. Silent no-op when GBrain is unreachable or no token is set. Disclosure — before each non-trivial turn the last six user and assistant messages (truncated) and the current message are sent with a GBRAIN_TOKEN bearer token to GBRAIN_MCP_URL (default http://127.0.0.1:3131/mcp), and returned brain-page text is injected into the turn."
  5. maintainer: aean0x
  6. tier: community
  7. category: memory
  8. docs_url: https://github.com/aean0x/hermes-gbrain-retrieval-reflex#readme
  9. version: "0.6.1"
  10. capabilities:
  11. provides_tools: []
  12. provides_hooks:
  13. - pre_llm_call
  14. provides_middleware: []
  15. requires_env: []