Browse Agents

Scan agent skills, plugins, and MCP servers before installing them — detects prompt injection, data exfiltration, malic…

Adds programmable guardrails to LLM apps — input/output moderation, jailbreak and prompt-injection detection, topic con…

Connects, profiles, evaluates, and optimizes agent workflows across frameworks like LangChain, LlamaIndex, and CrewAI,…

Open-source security runtime for multi-agent AI. Enforces policy-based access control, sandboxes kernel interactions, a…

Serves open models as NVIDIA-hosted NIM endpoints through an OpenAI-compatible API, with chat, embedding, reranking and…

Runs autonomous agents in isolated sandboxes with kernel-level policy enforcement over files, syscalls, and network, in…

Extends the Pi agent harness with AutoResearch loops from NVIDIA, improving efficiency on long-running autonomous resea…