llm-antidote.yaml 1.6 KB

123456789101112131415161718192021
  1. name: llm-antidote
  2. repo: https://github.com/GroveMinting/llmAntidote
  3. sha: c7f6a5428abbdba2b48f8b5fd3494b7ae2e3c5e8
  4. description: "Runtime guardrails, behavioral evaluation, and signed fleet admission for Hermes Agent: a versioned capability policy that blocks or requires approval for model tool calls, paired synthetic behavioral evaluation with no real side effects, and a signed local promotion gate that refuses a model whose evidence does not satisfy signed fleet policy. Hooks-only (no agent tools). Disclosure — Adds approval prompts to tool calls by default (balanced mode): every MCP, connector or other-plugin tool, memory and skill writes, file reads outside the working and temp directories, and network-capable terminal/code commands go to Hermes's approval prompt; strict mode blocks them instead, and opt-in enforced fleet mode blocks all tool calls until the served model name matches the admitted one. The user-run `hermes antidote eval run` command sends synthetic prompts (and the API key you name) to the OpenAI-compatible endpoint you pass, as billed model calls (default suite up to ~170 requests); `model inspect hf:` queries huggingface.co; `fleet keygen` writes unencrypted Ed25519 private keys (mode 0600) to paths you choose."
  5. maintainer: GroveMinting
  6. tier: community
  7. category: tools
  8. requires_hermes: ">=0.21.5"
  9. version: "3.2.4"
  10. docs_url: https://github.com/GroveMinting/llmAntidote#readme
  11. capabilities:
  12. provides_tools: []
  13. provides_hooks:
  14. - pre_tool_call
  15. - post_tool_call
  16. - pre_api_request
  17. - on_session_start
  18. - on_session_reset
  19. - on_session_finalize
  20. provides_middleware: []
  21. requires_env: []