hermes-labs-ai

by Hermes Labs

Returns concise LintLang repair guidance after Claude Code changes a supported language-bearing file.

by Hermes Labs

Blocks a Claude Code turn when a local Little Canary server rejects the submitted prompt.

by Hermes Labs

Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts

by Hermes Labs

Local recovery anchors for Claude Code and Codex sessions, plus evidence-gated evaluation prompts

by Rolando Bosch

Legacy advisory Stop-hook bundle for the fixed English gate. Current Claude Stop compatibility is not certified in v0.1.7; use the CLI directly. Requires the hermeneutic package.

by Rolando Bosch

Advisory-only Stop-hook drift gate for Codex — regex-only, zero-LLM, no network.

by Hermes Labs

Run the released Quick Gate CLI ([email protected]) as one deterministic JavaScript/TypeScript gate and read its gate-result/v1 verdict

by Hermes Labs

Jailbreak regression benchmark for LLM endpoints with repeatable known-pattern attacks and deterministic scoring

by Hermes Labs

On-demand static analysis of AI system prompts: audit a prompt file for contradictions, coverage gaps, priority ambiguities and meta-paradoxes, locally and offline.

by Hermes Labs

Bounded public search evidence with source-explicit supersearch.search.v1 receipts (pinned hermes-supersearch 0.11.0); evidence, not answers

by Hermes Labs

A guided, project-local first experience for Claude Code that helps beginners start making something real.

by Rolando Bosch

Road signs for coding agents: a PreToolUse hook that reports when the file you're about to touch is in a git checkout behind its upstream, and stays silent otherwise.

by Hermes Labs

Recoverable deletion for coding agents: move files to trash, list them, and restore them with agent-trash.

by Hermes Labs

Blocks permanent-delete shell commands in Codex and redirects agents to a recoverable trash workflow.

by Hermes Labs

Blocks permanent-delete shell commands in Claude Code and redirects agents to a recoverable trash workflow.

by Hermes Labs

CSV preflight validation and batch CSV quality checks that fail fast before pipeline runs.

by Hermes Labs

Receipt-bound completion rail for Claude Code: SessionStart injects the completion contract, Stop runs the cached fast gate advisory-only, and PreToolUse denies a Bash commit/push/PR boundary command missing its matching receipt.

by Rolando Bosch

Map markdown acceptance items to explicit implementation evidence for advisory spec-drift checks.

by Hermes Labs

Python quality gate CLI for Ruff, Pyright, and pytest with bounded auto-repair and escalation artifacts