1 person.1,000 agents.
Ready Agents.·Real Work.Build your AI team. It's easy.
Plan, market, ship, support — every function of your work, run by specialists who remember, collaborate, and answer to you alone.
Stop juggling.
Start operating.
From AI tools to an AI team.
A chatbot can answer. A single AI tool can do one task. But real work needs planning, splitting, execution, review, and memory.
CrewX turns the AI tools you already use into a role-based team: a supervisor assigns the work, AI workers execute in parallel, reviewers check the result, and every decision stays in context — across engineering, design, content, support, and analytics.
You supervise the work from the browser. CrewX handles threads, roles, memory, and handoffs so you stop juggling prompts and start operating an AI-native team.
Multi-provider orchestration
Mix Claude, Gemini, Codex, Copilot, OpenCode in a single crew — Claude plans & reviews, Codex verifies, Gemini researches, Copilot runs personas, OpenCode handles bulk.
Work Instructions (WI)
The PM agent writes structured tickets, then dispatches them to workers. Threaded, traceable, replayable — every change has a paper trail.
Threaded conversations
Each topic lives in its own thread with full history. Agents keep context across days — no more re-pasting your stack.
Long-term memory
Agents save decisions, knowhow, and worklogs as Markdown. BM25-indexed, model-readable, version-controlled with your repo.
Skills & built-in tools
Drop-in skills for memory, search, docs, code review. Compose them per agent. Build your own with a single SKILL.md.
Hooks & automations
Pre/post-tool hooks, scheduled jobs, custom slash commands. Wire CrewX into your existing workflow without leaving the browser.
Pick the right model
per role.
Each tool earns its role from how developers actually use it. Swap any time — no prompt rewrites, no lock-in.
- · Opus 4.7 / Sonnet 4.6
- · Plan Mode · 1M context
- · Role: Planner & Reviewer
- · 3 Pro / Flash
- · Live web grounding
- · Role: Researcher
- · GPT-5.1-Codex
- · Adversarial review · race conditions
- · Role: Verifier
- · GPT / Claude / Gemini / o3
- · Pick model per task
- · Role: Persona simulator
- · GLM / Qwen / DeepSeek / Kimi
- · Local via Ollama / LM Studio
- · Role: Bulk worker · low-sensitivity
Pay for the wrapper.
Not the AI.
Use the AI subscriptions you already pay for — Claude Code, Codex, Gemini CLI, Copilot CLI. We never charge a token markup.
Free
Try it. Create your first agent.
Start Free- Workflows10
- Agents (per WS)10
- Projects10
- Workspaces3
- ✓ Web UI (no install)
- ✓ Bring your own AI subscriptions
Basic
Solo builders. First real workflows.
Start with Basic- Workflows20
- Agents (per WS)20
- Projects20
- Workspaces10
- ✓ Community support
Pro
Power users. 1,000 agents in one workspace org.
Get Pro- Workflows100
- Agents (per WS)100
- Projects40
- Workspaces10
- Total agents1,000 ✦
All plans use the AI subscriptions you already pay for — Claude Code, Codex, Gemini CLI, Copilot CLI. CrewX charges 0% token markup.