22 projects
hermes-rubric
Evidence-first structured scoring. Class-aware rubric templates for deterministic dim sets across runs.
langstate
Scaffold-aware context compression for OpenAI-format messages — preserve state at 50%+ token reduction via local Ollama, OpenAI, or Anthropic
pygate-ci
Python quality gate CLI for Ruff, Pyright, and pytest with bounded auto-repair and escalation artifacts
repo-readiness
GitHub repo launch-readiness auditor — signals your repo is missing for public discoverability.
zer0lint
AI memory extraction diagnostics — works with mem0 or any HTTP memory endpoint. By Hermes Labs.
cogito-ergo
Memory retrieval for AI agents — integer-pointer fidelity guarantee, 93.4% R@1 on LongMemEval_S (hybrid tier). By Hermes Labs.
hermes-repo-audit
GitHub repo launch-readiness auditor — signals your repo is missing for public discoverability.
scaffold-lint
Static linter for LLM prompt scaffolds — catches oversized scaffolds and incompatible technique mixes (evidential + step-by-step + format).
intent-verify
Repo intent verification and spec drift checks for markdown specs, handoffs, and codebases.
csv-quality-gate
CSV preflight validation and batch CSV quality checks that fail fast before pipeline runs.
langquant
LPCI: Statefulness Through Language for Stateless Models
agent-convergence-scorer
Score how similar N agent outputs are — exact match, Jaccard token overlap, divergence point, composite 0-1 score. Stdlib-only.
rule-audit
Detect logical contradictions, gaps, and exploitable edge cases in AI system prompts
colony-probe
Offensive AI red-team tool: multi-turn 'innocent question' sequences for system prompt reconstruction.
hermes-jailbench
Automated jailbreak testing CLI — run a battery of known attack patterns against any LLM endpoint
hermes-jailbreak-bench
Automated jailbreak testing CLI — run a battery of known attack patterns against any LLM endpoint
claude-router
Embedding-based scaffold router for Claude API. Routes tasks to the right scaffold using centroid matching. By Hermes Labs.
lintlang
Linter for AI agent tool descriptions, system prompts, and configs. Catches vague instructions, missing constraints, and schema mismatches. By Hermes Labs.
zer0dex
Dual-layer memory for AI agents. Compressed index + vector store. 91% recall, 70ms, $0/month.
forgetted
Selective memory governance for AI agents — branch the timeline, never merge back
suy-sideguy
Runtime safety guard for autonomous AI agents
little-canary
Sacrificial LLM instances as behavioral probes for prompt injection detection
