Pinned Loading

1. hermes-labs-ai/little-canary hermes-labs-ai/little-canary Public

   little-canary is a prompt-injection detector that reads attacks by their effect on a sacrificial canary model before they reach production. Puts a small canary model in front of your app, watches w…

   Python 22 5

2. hermes-labs-ai/lintlang hermes-labs-ai/lintlang Public

   lintlang is a static linter for AI agent configs, tool descriptions, and system prompts that runs zero-LLM quality gating in CI. Catches language-level failures (vague tool descriptions, missing st…

   Python 48 2

3. hermes-labs-ai/zer0dex hermes-labs-ai/zer0dex Public

   zer0dex is a local dual-layer memory pattern for AI agents: a compressed, human-readable markdown index plus a vector store queried automatically before each message. Built for cross-project recall…

   Python 54 3

4. hermes-labs-ai/quick-gate-js hermes-labs-ai/quick-gate-js Public

   quick-gate-js (npm: quick-gate) is a deterministic JS/TS CI quality gate that unifies ESLint, TypeScript, build, and Lighthouse checks into one fail-fast result, with bounded auto-repair and struct…

   JavaScript 3

5. hermes-labs-ai/quick-gate-python hermes-labs-ai/quick-gate-python Public

   quick-gate-python (PyPI: pygate-ci) is a deterministic Python CI quality gate that normalizes Ruff, Pyright, and pytest results into one fail-fast decision, attempts bounded auto-repair, and escala…

   Python

6. hermes-labs-ai/agent-warden hermes-labs-ai/agent-warden Public

   agent-warden is a runtime policy guard for autonomous AI agents that enforces kill/flag policy on a live agent process and emits a forensic report of what it did. Scores file, network, and subproce…

   Python