Hermes Labs
- 7 followers
- San Francisco, CA
- https://hermes-labs.ai
- @rolibosch
- rbosh@lpci.ai
Popular repositories Loading
-
little-canary
little-canary PublicPrompt injection detection for LLM apps using sacrificial canary-model probes and structural preflight checks
-
hermes-blind
hermes-blind PublicContext-compensation scaffold for LLM evaluation prompts — disclose, gate on evidence, hedge on thin
Python 3
-
quick-gate-js
quick-gate-js PublicJavaScript and TypeScript quality gate CLI with bounded auto-repair and escalation artifacts
JavaScript 2
Repositories
- little-canary Public
Prompt injection detection for LLM apps using sacrificial canary-model probes and structural preflight checks
hermes-labs-ai/little-canary’s past year of commit activity - fidelis Public
Agent memory without the retrieval tax. Fidelity-preserving memory for Claude Code and AI agents — local-first, fast, and with no LLM in the default retrieval path. 83.2% R@1 on LongMemEval-S, $0/query retrieval.
hermes-labs-ai/fidelis’s past year of commit activity - suy-sideguy Public
Runtime policy guard for autonomous AI agents with user-space enforcement and forensic reporting
hermes-labs-ai/suy-sideguy’s past year of commit activity - scaffold-lint Public
Static linter for LLM prompt scaffolds — catches oversized scaffolds and incompatible technique mixes. Stdlib-only.
hermes-labs-ai/scaffold-lint’s past year of commit activity - rule-audit Public
Static prompt audit CLI for LLM system prompts: contradictions, coverage gaps, priority ambiguities, and edge-case checks
hermes-labs-ai/rule-audit’s past year of commit activity - repo-readiness Public
15-second launch-readiness audit for GitHub repos. 9 signals (README, PyPI, docs, topics, stars, citations, launch channels), source-backed, honest nulls. pip install repo-readiness.
hermes-labs-ai/repo-readiness’s past year of commit activity - quickthink Public
Local-first inference control layer for small LLMs. Inline plan-then-answer scaffolding (lite/two_pass/direct) for more reliable structured outputs at lower latency on Ollama and similar.
hermes-labs-ai/quickthink’s past year of commit activity
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…