Todas las etiquetas
Etiqueta del catálogo

#agent-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.

13 registros
Con la etiqueta «agent-safety»Ordenado por índice de salud
PyPI
87Excelenteíndice de salud
sattyamjjain/agent-airlock
A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.
Python★ 15↓ 3569/mes18 sept 2026
Apache-2.018 sept 2026 · métricas 2.10.0
npm
86Excelenteíndice de salud
emiliaprotocol/emilia-protocol
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
TypeScript · HTML★ 649↓ 1109/mes5 sept 2026
Apache-2.05 sept 2026 · métricas 2.10.0
npm
84Excelenteíndice de salud
runcycles/cycles-mcp-server
MCP budget and risk authority for Cycles — runtime governance for Claude, Cursor, and Windsurf
TypeScript★ 0↓ 393/mes7 sept 2026
Apache-2.07 sept 2026 · métricas 2.10.0
npm
83Excelenteíndice de salud
runcycles/cycles-openclaw-budget-guard
Cycles budget and action guard for OpenClaw agents
TypeScript★ 7↓ 86/mes20 sept 2026
Apache-2.020 sept 2026 · métricas 2.10.0
npm
81Excelenteíndice de salud
lua-ai-global/governance
Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
TypeScript★ 26↓ 18.7K/mes13 sept 2026
MIT13 sept 2026 · métricas 2.10.0
PyPI
77Buenoíndice de salud
shcherbak-ai/tethered
tethered - Runtime network egress control for Python. One function call to restrict which hosts your code can connect to.
Python★ 10↓ 6116/mes14 oct 2026
MIT14 oct 2026 · métricas 2.10.0
PyPI · npm
73Buenoíndice de salud
CaspianG/wavemind
Verified experience for AI agents: independently checked, scoped, cited, and reversible.
Python★ 7↓ 494/mes20 oct 2026
MIT20 oct 2026 · métricas 2.10.0
PyPI
71Buenoíndice de salud
philpaz/recusal
Deterministic governance for Claude and MCP tool calls. Pin approved capabilities, detect drift, and refuse unsafe or unapproved actions before execution. No model in the decision path.
Python★ 4↓ 419/mes14 sept 2026
Apache-2.014 sept 2026 · métricas 2.10.0
npm · PyPI
65Buenoíndice de salud
stylusnexus/agent-armor
Open-source agent security framework. Detects and defends against AI Agent Traps — content injection, embedded jailbreaks, RAG poisoning, data exfiltration, and more. Based on the DeepMind Agent Traps taxonomy.
TypeScript · Python★ 4↓ 1659/mes18 sept 2026
MIT18 sept 2026 · métricas 2.10.0
npm · PyPI
60Moderadoíndice de salud
CogNEXUSlabs/cognexus-tools
CogNEXUS Labs builds the infrastructure that makes autonomous AI accountable to the enterprise. Our product, Artzain is the model-agnostic Agent Control Plane for autonomous systems. Here's the SDK
Python · TypeScript★ 1↓ 2494/mes18 sept 2026
Apache-2.018 sept 2026 · métricas 2.10.0
Go
60Moderadoíndice de salud
hyj28/unring
Reversible side effects for AI coding agents — snapshot files, hold PostgreSQL writes, and review outbound actions before they become permanent.
Go★ 319 sept 2026
MIT19 sept 2026 · métricas 2.10.0
Go
56Moderadoíndice de salud
PayCal-Technologies/vigil-public
Repository preflight and agent-safety CLI for local automation evidence
HTML · Go★ 020 sept 2026
0BSD20 sept 2026 · métricas 2.10.0
PyPI
41Débilíndice de salud
thomasjgeorge23/agent-saga
El repositorio no publica descripción.
Python★ 2↓ 3473/mes15 sept 2026
Apache-2.015 sept 2026 · métricas 2.10.0