PyPI
provael/provael
Provael — red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR). Prove it. Prevail.
Apache-2.019 jul 2026 · métricas 2.10.0
Todas las etiquetas
Etiqueta del catálogo
#ai-safety
Todos los repositorios del registro público que llevan esta etiqueta, procedente de sus topics de GitHub o de las palabras clave que publican sus registros de paquetes. La salud se mide con la misma metodología versionada que el resto del registro.
42 registros
PyPI
EgisLabs/egisai-sdk
EgisAI SDK
Apache-2.01 ago 2026 · métricas 2.10.0
npm
neuradex/llm-rail
Deterministic workflow control CLI for LLM (Coding) agents
MIT5 sept 2026 · métricas 2.10.0
npm
agledger-ai/sdk
AGLedger™ SDK — Accountability and audit infrastructure for agentic systems. Patent Pending.
Licencia propia15 jul 2026 · métricas 2.10.0
PyPI
rozmiard/sclite
Schema-backed contract layer for governed AI/security workflows: intent, policy decisions, approvals, execution receipts, evidence, and replayable audit traces.
MIT18 jul 2026 · métricas 2.10.0
Go
AccursedGalaxy/driver-os
Verifiable coding-agent harness in Go: external test gates, typed outcomes, sandboxed execution, multi-model providers, and signed proof bundles.
MIT30 ago 2026 · métricas 2.10.0
Go
loop-eng/loopguard
Circuit breaker daemon for AI agent loops
MIT25 ago 2026 · métricas 2.10.0
Go
nlink-jp/mcp-guardian
MCP governance proxy - zero-dependency single binary (Go)
MIT19 jul 2026 · métricas 2.10.0
PyPI
vdalal/agentx-security-sdk
Runtime action firewall for AI agents: the keyless Shield. Blocks catastrophic tool calls (DROP TABLE, SSRF, secret exfil) in-process, no key. MIT.
MIT19 jul 2026 · métricas 2.10.0
npm · crates.io
wiber/thetacog-mcp
npx thetacog-mcp — a decidable, on-chip, LLM-free placement receipt a stranger recomputes byte-for-byte. Free for builders; patent-licensed for production & financial use (US Patent App. 19/637,714).
Licencia propia23 jul 2026 · métricas 2.10.0
npm
jyswee/a2a-trustgate
Compliance for AI systems in production — screen every AI-agent action through a 4-gate firewall before it runs, with an OCSF-native audit trail mapped to EU AI Act / SOC 2 / NIST / HIPAA.
Licencia propia22 jul 2026 · métricas 2.10.0
npm
golproductions/check
The anti-hallucination layer for AI agents.
Licencia propia5 sept 2026 · métricas 2.10.0