agentos
01Plugin Claude Code
Agent Operating System — self-evolving agents, multi-agent orchestration, 25-screen TUI, 25 LLM providers. Built on iii-engine.
Plugin Claude Code
Agent Operating System — self-evolving agents, multi-agent orchestration, 25-screen TUI, 25 LLM providers. Built on iii-engine.
MCP server Claude CodeCodexCursor +2
MCP server "agentos" as configured in iii-experimental/agentos. Runs locally from the agentos npm package.
Agent
Software engineer — implements features, writes tests, fixes bugs.
Agent
Multi-agent coordinator — plans features, decomposes tasks, spawns workers.
Agent
Research and analysis agent — gathers context, explores codebases, summarizes findings.
Agent
Code review agent — reviews diffs, checks quality, suggests improvements.
Agent
Security audit agent — scans for vulnerabilities, checks permissions, reviews secrets.
Command
Send a message to an AgentOS agent.
Command
Quick evolve a function — generate, register, and evaluate.
Command
Quick orchestrate a feature — decompose, plan, and execute.
Command
Show AgentOS system status — agents, workers, health.
Command
Launch the AgentOS TUI dashboard.
Hook
Runs before the agent uses a tool for ^(Write and Edit)$ tool calls, running an inline shell check. From iii-experimental/agentos.
Hook
Runs when the agent finishes a response, running an inline shell check. From iii-experimental/agentos.
Skill Claude CodeCodex
Create, test, and improve functions at runtime — agents write their own code.
Skill Claude CodeCodex
Session lifecycle management — transitions, state tracking, reactions.
Skill Claude CodeCodex
Persistent agent memory — store, recall, search across sessions.
Skill Claude CodeCodex
Plan and execute multi-agent work — decompose features, spawn workers, monitor progress.
Skill Claude CodeCodex
Scan agent health and auto-recover stale or dead sessions.
Skill Claude CodeCodex
Security scanning — injection detection, capability checks, audit trails.
Skill Claude CodeCodex
System status and health checks — dashboard stats, agent health, worker status.
Skill Claude CodeCodex
Multi-agent swarm coordination — create swarms, broadcast tasks, reach consensus.
Skill Claude CodeCodex
Task decomposition — break features into subtasks, assign workers, track progress.
Skill Claude CodeCodex
Secret management — encrypted storage for API keys, tokens, credentials.