PlanExe

Turn your idea into a comprehensive plan in minutes, not months.

PlanExe is the premier planning tool for AI agents.

---

Example plans generated with PlanExe

• A business plan for a Minecraft-themed escape room.
• A business plan for a Faraday cage manufacturing company.
• A pilot project for a Human as-a Service.
• See more examples here.

What is PlanExe?

PlanExe is an open-source tool and the premier planning tool for AI agents. It turns a single plain-english goal statement into a 40-page, strategic plan in ~15 minutes using local or cloud models. It's an accelerator for outlines, but no silver bullet for polished plans.

Typical output contains:

• Executive summary
• Gantt chart
• Governance structure
• Role descriptions
• Stakeholder maps
• Risk registers
• SWOT analyses

The technical quality of structure, formatting, and coherence is consistently excellent—often superior to human junior/mid-tier consulting drafts. However, budgets remain headline-only, timelines contain errors, metrics are usually vague, and legal/operational realism is weak on high-stakes topics. A usable, client-ready version still requires weeks to months of skilled human refinement.

PlanExe removes 70–90 % of the labor for the planning scaffold on any topic, but the final 10–30 % that separates a polished document from a credible, defensible plan remains human-only work.

---

New to PlanExe? Follow the Getting Started guide.

Model Context Protocol (MCP)

PlanExe exposes an MCP server for AI agents at https://mcp.planexe.org/

Assuming you have an MCP-compatible client (OpenClaw, Cursor, Codex, LM Studio, Windsurf, Inspector).

The Tool workflow (tools-only, not MCP tasks protocol)

1. prompt_examples
2. task_create
3. task_status (poll every 5 minutes until done)
4. download the result via task_download or via task_file_info

Option A: Remote MCP (fastest path)

Prerequisites

• An account at https://home.planexe.org.
• Sufficient funds to create plans.
• A PlanExe API key (pex_...) from your account

Use this endpoint directly in your MCP client:

{
  "mcpServers": {
    "planexe": {
      "url": "https://mcp.planexe.org/mcp",
      "headers": {
        "X-API-Key": "pex_your_api_key_here"
      }
    }
  }
}

Option B: Remote MCP + local downloads via proxy (mcp_local)

If you want artifacts saved directly to your disk from your MCP client, run the local proxy:

{
  "mcpServers": {
    "planexe": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp",
        "/absolute/path/to/PlanExe/mcp_local/planexe_mcp_local.py"
      ],
      "env": {
        "PLANEXE_URL": "https://mcp.planexe.org/mcp",
        "PLANEXE_MCP_API_KEY": "pex_your_api_key_here",
        "PLANEXE_PATH": "/absolute/path/for/downloads"
      }
    }
  }
}

Option C: Run MCP server locally with Docker

Prerequisites

• Docker
• OpenRouter account
• Create a PlanExe .env file with OPENROUTER_API_KEY.

Start the full stack:

docker compose up --build

Make sure that you can create plans in the web interface, before proceeding to MCP.

Then connect your client to:

• http://localhost:8001/mcp

For local docker defaults, auth is disabled in docker-compose.yml.

Local file downloads via proxy (mcp_local)

If you want artifacts saved directly to your disk from your MCP client, run the local proxy:

{
  "mcpServers": {
    "planexe": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp",
        "/absolute/path/to/PlanExe/mcp_local/planexe_mcp_local.py"
      ],
      "env": {
        "PLANEXE_URL": "http://localhost:8001/mcp/",
        "PLANEXE_PATH": "/absolute/path/for/downloads"
      }
    }
  }
}

MCP docs

• Setup overview: https://docs.planexe.org/mcp/mcp_setup/
• Tool details and flow: https://docs.planexe.org/mcp/mcp_details/
• MCP Inspector guide: https://docs.planexe.org/mcp/inspector/
• Cursor setup: https://docs.planexe.org/mcp/cursor/
• Codex setup: https://docs.planexe.org/mcp/codex/
• PlanExe MCP interface: https://docs.planexe.org/mcp/planexe_mcp_interface/
• MCP Registry publishing metadata (server.json): mcp_cloud/server.json
• llms.txt: https://mcp.planexe.org/llms.txt

Try it out now (Click to expand)

You can generate 1 plan for free.

Try it here →

---

Run locally with Docker (Click to expand)

Prerequisite: Docker with Docker Compose installed; you only need basic Docker knowledge. No local Python setup is required because everything runs in containers.

Quickstart: single-user UI + worker (frontend_single_user + worker_plan)

1. Clone the repo and enter it:

git clone https://github.com/PlanExeOrg/PlanExe.git
cd PlanExe

2. Provide an LLM provider. Copy .env.docker-example to .env and fill in OPENROUTER_API_KEY with your key from OpenRouter. The containers mount .env and llm_config/; pick a model profile there. For host-side Ollama, use the docker-ollama-llama3.1 entry and ensure Ollama is listening on http://host.docker.internal:11434.

3. Start the stack (first run builds the images):

docker compose up worker_plan frontend_single_user

The worker listens on http://localhost:8000 and the UI comes up on http://localhost:7860 after the worker healthcheck passes.

4. Open http://localhost:7860 in your browser. Optional: set PLANEXE_PASSWORD in .env to require a password. Enter your idea, click the generate button, and watch progress with:

docker compose logs -f worker_plan

Outputs are written to run/ on the host (mounted into both containers).

5. Stop with Ctrl+C (or docker compose down). Rebuild after code/dependency changes:

docker compose build --no-cache worker_plan frontend_single_user

For compose tips, alternate ports, or troubleshooting, see docs/docker.md or docker-compose.md.

Configuration

Config A: Run a model in the cloud using a paid provider. Follow the instructions in OpenRouter.

Config B: Run models locally on a high-end computer. Follow the instructions for either Ollama or LM Studio. When using host-side tools with Docker, point the model URL at the host (for example http://host.docker.internal:11434 for Ollama).

Recommendation: I recommend Config A as it offers the most straightforward path to getting PlanExe working reliably.

---

Screenshots (Click to expand)

You input a vague description of what you want and PlanExe outputs a plan.

YouTube video: Using PlanExe to plan a lunar base

---

Help (Click to expand)

For help or feedback.

Join the PlanExe Discord.