published by hermes-labs-ai
7 tools
- fidelisLocal agent memory with verbatim records, correction history, and time-aware recall. Provides fidelis_recall, fidelis_store, fidelis_correct25 stars
- hermeneuticDeterministic epistemic checks for Gemini CLI final responses, with one bounded automatic repair attempt.9 stars
- hermes-blindLocal recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts10 stars
- hermes-jailbenchJailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring12 stars
- lintlangReturns concise LintLang repair guidance after Gemini CLI changes language-bearing files.147 stars
- little-canaryBlocks Gemini CLI agent runs when a local Little Canary server rejects the prompt.41 stars
- supersearchBounded public search evidence with source-explicit supersearch.search.v1 receipts (pinned hermes-supersearch 0.11.0); evidence, not answers3 stars