Guardrails & SafetyFree
Vultrino
Vultrino runs as a self-hosted credential proxy: agents reference an alias like 'github', and Vultrino injects the real token server-side…
VerifiedOSS
View VultrinoGuardrails & Safety
LLM guardrails and safety filters.
Guardrails & SafetyFree
Argot
Argot runs statistical checks against your repository's own commit history to flag code that looks foreign to the codebase — wrong…
VerifiedOSS
View Argot
Guardrails & SafetyPaid
NeuralTrust TrustGate
NeuralTrust TrustGate sits between your agents and the models, tools, and services they reach, enforcing policy at the interaction level…
VerifiedOSS
View NeuralTrust TrustGate
Guardrails & SafetyFree
ButterClaw
ButterClaw runs as a self-hosted security monitor for AI agent deployments, watching post-authorization behavior for prompt injection…
VerifiedOSS
View ButterClaw
Guardrails & SafetyFree
ASL V6
ASL V6 combines AST-based static analysis with Docker-isolated runtime verification to find and confirm exploitable vulnerabilities in AI…
VerifiedOSS
View ASL V6
Guardrails & SafetyFree
ModelFuzz
The library ships two halves: a red-team scanner that fires deceptive prompt-injection payloads at any OpenAI-compatible endpoint so you…
VerifiedOSS
View ModelFuzz
Guardrails & SafetyFreemium
Axtary
Axtary sits beside the agent and evaluates each tool call against deterministic policy before the underlying provider is called. Routine…
VerifiedFreemium
View Axtary
Guardrails & SafetyFree
OpenTrust
OpenTrust runs in the browser, gathers signals about the environment and interaction patterns, and returns a trust score your server can…
VerifiedOSS
View OpenTrust
Guardrails & SafetyFree
QuantmLayer
QuantmLayer installs as a single static binary and builds a least-privilege cell from Linux kernel primitives — six enforced walls covering…
VerifiedOSS
View QuantmLayer
Guardrails & SafetyFree
Panguard.AI
Panguard installs in one command, runs entirely offline with zero telemetry, and auto-detects agents across a wide surface — Claude Code…
VerifiedOSS
View Panguard.AI