Deep Agents
Library for building agents with planning, filesystem access, and subagents.
LangChainHow skills run on Deep Agents
Deep Agents is a Python and JavaScript harness built on LangGraph, with filesystem backends, subagent delegation, and MCP connections. Skills loaded into an agent built this way inherit whatever tools the developer wired up, including database and API access.
Skill security, assessed
Every public skill in our index is assessed by the Anomity Skill Intelligence engine against its real source: remote code execution, credential and data exfiltration, prompt injection, and unsafe installers.
Govern the skill layer on Deep Agents
Scanning a skill before use tells you what it claims to do. Anomity's Endpoint Sensor sees what agents actually do at runtime: it discovers every skill, agent, and MCP server on the endpoint, and policy can allow, deny, or log the tool calls a skill triggers on Deep Agents and every other agent. Violations route to your SIEM, Slack, email, or Jira with a queryable 90-day audit trail.
Book a 30-minute demo to see your own agent and skill inventory.
