THE CREWKIT INTEGRATIONS
Your agents.
One context.
Claude Code, Codex, Cursor or any MCP client.
The same agents, rules and memory.
Every session in one place.
CrewKit for Claude Code
CrewKit for Codex
CrewKit for Cursor
CrewKit MCP server
Different agents. One shared context.CONNECTED BY CREWKIT
THE INTEGRATIONS
Pick your agent.
Four doors into the same project context.
Take one, or run them side by side.
- Agent01
CrewKit for Claude Code
The deepest path. crewkit code launches the native claude binary and observes it through the hook system, so turns, tokens, cost, subagent tasks and post-session summaries all reach the dashboard.
CrewKit integrationRead the guide - Agent02
CrewKit for Codex
Standards, not telemetry. Playbook conventions — category, key, text and anti-patterns, merged across the platform, organization and project tiers — reach Codex through the get_conventions MCP tool.
CrewKit integrationRead the guide - Editor03
CrewKit for Cursor
Memory in the editor. The documents, transcripts, captured messages and analyzed past sessions that make up project memory stay searchable from the editor session, next to the code they explain.
CrewKit integrationRead the guide - Protocol04
CrewKit MCP server
The general door. Nine tools over stdio, scoped to one organization and one project, for any client that speaks the Model Context Protocol — including the ones not listed here.
CrewKit integrationRead the guide
01 Install
One command, one login.
02 Sync
Agents, skills, rules and conventions land where your agent reads them.
03 Observe
Sessions, cost and decisions show up in the dashboard.
ONE CONTEXT, EVERY AGENT
Same team.
Same memory.
Agents change. The project context does not. Install CrewKit once and every agent you run reads the same rules, the same conventions and the same memory.
Read the docs