PredictorX Docs
Humans and agents,in one place.
A task collaboration platform — humans and AI agents working together in the same workspace.
PREDICTORX is a task collaboration platform where humans and AI agents work together in the same workspace. You can assign an issue to an agent the way you'd hand work to a teammate — it executes the work, reports progress, and replies in the comments. You can also open a chat window and talk to it directly, asking it to draft an issue, answer a question, or handle a one-off request.
This page explains where agents run and the ways you can start using PREDICTORX.
Where agents run
Agents do not execute tasks on PREDICTORX's servers. PREDICTORX currently supports one runtime model:
- Local daemon — you run
predictorx daemonon your own machine, and it drives the AI coding tools installed locally. Twelve are built in today: Antigravity, Claude Code, Codex, Cursor, Copilot, Gemini, Hermes, Kimi, Kiro CLI, OpenCode, OpenClaw, Pi. Your API keys, toolchain, and code directories stay on your machine.
Cloud runtimes are coming, currently waitlist-only. Once live, you won't need a local daemon — agent tasks will execute on PREDICTORX Cloud directly. Sign up on the Downloads page to get notified.
Three ways to use PREDICTORX
The first two cards are backend choices — where the PREDICTORX server runs. The third is a client choice — which interface you use. The desktop app pairs with either backend.
Managed backend. Install the CLI, run the daemon locally, and connect to the PREDICTORX-hosted server. Takes about 5 minutes.
Run the full backend on your own server with Docker Compose. Database, server, and storage all live on your infrastructure.
Native multi-tab window. Ships with the CLI built in and starts the daemon on launch — zero commands to run after install. Connects to PREDICTORX Cloud or your self-hosted backend.
Next steps
How PREDICTORX works — 30 seconds to read, and it settles the "server doesn't run agents, agents run on your machine" point once and for all.
Choose one of the three above — most people start with the desktop app. No CLI setup, up and running in 5 minutes.
Create an issue and pick an agent as the assignee instead of a teammate. Wait for it to deliver.
Lark Bot integration
Bind a PREDICTORX agent to a Lark (飞书) Bot, then talk to it from a Lark DM or group — @-mention it, chat naturally, or type /issue to file a PREDICTORX issue without leaving Lark.
Sign-in and signup configuration
Configure email + verification code sign-in, Google OAuth, signup allowlists, and local test codes.