10 actions in 6 pieces of software · ranked by words, meaning and measured trust · 966 ms
modelrecord
- structured-outputs
Can return JSON matching a schema.
- text+image+file->text
Takes text, image, file; returns text.
- structured-outputs
modelrecord
- tool-calling
Can call tools (function calling).
- tool-calling
- 3grokfound in code, not yet checkedno passport yet
- grok_workflow
List or run Grok Rhai multi-agent workflows. Use action=list (read-only) or action=run.
- grok_workflow
- 4grok-bot-agent-mcpfound in code, not yet checkedno passport yet
MCP serveremrecengdev/grok-bot-agent-mcp
- grok_interrupt
Interrupt an agent run using the installed coordinator contract. No automatic retries.
- grok_call
Call a discovered coordinator method with its actual argument object. Inspect grok_capabilities first. Mutations require a stable request_key; timeout outcomes can be unknown and must not be blindly retried.
- grok_list_agents
List actual Grok Bot agents through the existing coordinator connection, not profile files.
- grok_search_agents
Search Grok Bot agents. Argument fields follow the installed app contract.
- grok_interrupt
skilldavila7/claude-code-templatesrecord
- crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangC
- crewai-multi-agent
- 6sgxfound in code, not yet checkedno passport yet
MCP servermikeyobrien/sgx
- research
Deep multi-agent research on grok-4.20-multi-agent.
- research
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.