Search

Inspectable LangGraph coding agent with verified patches, resumable trajectories, sandboxed tools, and HMAC-authenticated Undo.

Static repository guardrails for agent-touched codebases.

Static, reverse-engineering-assisted vulnerability triage for AI agents -- CLI + MCP server, no Ghidra required. For files you own or are authorized to test.

AI Agent Toolkit - CLI unificada para herramientas de desarrollo impulsadas por IA

A hardened, containerized environment for running Claude Code as an AI agent with access to local tools via the Model Context Protocol (MCP).

证据驱动的 FOFA 资产测绘智能体：自然语言侦察、AI 反思、CLI / MCP / Skill / REST API，以及经人工审批的 Nuclei 扫描。

High-performance Agent Name Service (ANS) resolver with semantic versioning, and Redis caching. Agent Name Service, developed under the OWASP GenAI Security Project – Agentic Security Initiative, is a secure, DNS-inspired framework for AI agent discovery.

Data loss prevention for AI agents. Inspect what an agent is about to do, before it does it.

Sentinel registry proxy: transparently serves npm packages while intercepting and auditing each tarball, with an authoritative native publish path, verified claims, and time-locked retraction.

Safety-ranked open-source component discovery across npm, PyPI, GitHub, and Hugging Face for humans and AI agents.

AutoGen / OpenAI function-calling integration for the Grantex delegated authorization protocol

Sentinel CLI: pre-install audit verdicts, whole-tree lockfile audits, registry-redirected npm/npx, policy tooling, and sandbox-enforced installs.

Sentinel namespace-claim steward: DNS TXT claim verification, renewal/freeze lifecycle, timelocked transfers, and Ed25519-signed claim/retraction corpus releases.

Error with more than just a message, stacktrace parsing.

Sentinel capability sandbox: generate an OS sandbox profile from approved capabilities and run lifecycle scripts under it (macOS Seatbelt / Linux bubblewrap, deny-by-default).

Sentinel CI runner: self-booting dependency-tree audit for GitHub Actions (sentinel-ci) — audits a lockfile, writes a CycloneDX SBOM, and posts a PR verdict.

Offline authorization adapter for Google Gemma on-device AI agents

Deterministic access control for LangGraph agents.

LangChain integration for the Grantex delegated authorization protocol

AgentGuard Spend plugin for Hermes Agent (Nous Research). One-step install of local spend caps + signed audit logs for every Anthropic/OpenAI call your Hermes agent makes. No proxy, prompts never leave your machine.