Search

Cryptographic identity and trust for AI agents

AI model: AI45Research/AgentDoG1.5-FG-Llama-3.1-8B (text-classification)

AgentVisa credential presentation gateway

Generate adversarial test inputs with a coding agent; your pytest assertions judge them

Antarraksha AI Agent Enforcement SDK for Crewai

SENTINEL — Drop-in LLM Trust & Safety SDK. 19-agent parallel mesh: prompt injection, PII, jailbreak pattern detection, DAN attacks, cost anomaly detection, agentic loop breaking, hallucination, and compliance routing.

Monitors OpenClaw session files and sends all events to a Discord channel via webhook

Transparent MCP proxy for agent observability. Logs every tool call, exposes trace history, reduces token overhead.

Drop console.agent(...) anywhere in your code to execute agentic workflows — as easy as console.log()

AI skill: authentication and authorization conventions for web applications.

Portable OpenCode workflow plugins, explicit memory, and CLI tooling.

EYDII Verify tools for LlamaIndex — verify every agent action before execution

Runtime guardrails for AI coding agents: blocks dangerous commands, keeps secrets out of the model, and catches unverified 'tests pass' claims. Claude Code hooks, no dependencies.

LangChain middleware for the EISFI Weaver integrity chain: a tool call whose integrity precondition fails is never executed.

AI model: mradermacher/AgentDoG-Qwen2.5-7B-i1-GGUF

SAFER SDK — instrument any AI agent framework with one line. Hooks for Claude SDK, OpenAI, OpenAI Agents, LangChain, Google ADK, AWS Strands, AWS Bedrock, and CrewAI.

Human-in-the-loop pentest & OSINT CLI assistant

AI model: mradermacher/AgentDoG-Llama3.1-8B-GGUF

Agent Policy Engine is an AI agent enforcement runtime (PEP) that prevents untrusted data from becoming executable authority in AI agents

AI agent governance framework with audit trails, safety checks, and replayable decision making for autonomous systems