Pipeline
When the path is clear. You define the stages, runners, and approval points.
- A route that follows your project rules
- Checks and returns to the right stage
GrigDesk brings together AI agents, tasks, and development tools. You set the direction and approve the result.
Open source. Runs on Linux with your AI subscriptions and keys.
Agents move through the stages. The pipeline stops when it needs your decision. Try the example below.
Show products in stock at the selected warehouse.
AI agent runs this step
The agent locates the code and examines how the change relates to the rest of the project.
Choose a runner and model for each stage. Discuss tasks in chats and build a workflow for your project.
Planned integrations
One project. Different roles.
At your desk, on the move, or on the sofa. Your server runs the tasks. You connect from the device that suits you.
Tasks run on your Linux machine. Set up a direct connection or relay for remote access.
Connect your devicesDefine the sequence in advance or let a lead agent manage iterations. Final acceptance is always yours.
When the path is clear. You define the stages, runners, and approval points.
When the result needs iteration. A lead agent assigns tasks, reviews the work, and guides the runner.
Product availability filter
The lead assigns work and reviews every worker result.
Lead ⇄ Worker
Lead → Human acceptance
Handoffs to worker 0 / 4
Task stage 1 / 2
The task is a product availability filter for the selected warehouse. The lead splits work into implementation and verification.
Choose 2 to see a stop. The GrigDesk profile default is 20.
A prepared example without running AI or commands. Buttons advance the story; in GrigDesk the pair works automatically until acceptance or a stop.
Check the result in a preview environment. The project profile defines the working copy, containers, and data.
About previewsFrom reviewing changes to working with servers. Your tools stay alongside the task and your conversation with an agent.
The real GrigDesk interface with demo data. Open the screenshot to explore the details.
Files, search, changes, and Git history alongside your task.
SSH sessions with separate authorization for agent commands.
Connections, schemas, and queries in one panel.
Containers, Compose projects, and environment status.
Internal tasks, Bitrix24 and Jira Cloud on a shared board.
Turn meeting recordings into transcripts and tasks.
Create presentations with an enabled plugin.
Additional features depend on enabled plugins and configured connections.
For new behavior with clear acceptance criteria.
Plan → Implement → CheckExplore the exampleWhen you need to reproduce a defect and prove its cause first.
Cause → Fix → VerifyExplore the exampleWhen an improvement needs comparable measurements.
Measure → Change → CompareExplore the exampleFind more details
in the documentation.
Developers running their projects on Linux with AI agents. GrigDesk brings tasks, pipelines, chats and development tools into one application window.
In GrigDesk documentation this is called a loop. A lead agent assigns work to a worker, reviews results and manages stages until human acceptance. Handoffs are limited; lack of progress, unavailable environments and decisions outside agent authority require human intervention.
GrigDesk is open source under MIT and runs on your machine. Cloud AI access follows your providers’ terms, using your own keys or subscriptions.
Yes. Claude Code, OpenAI Codex, Kimi Code, DeepSeek and GLM (Z.ai) are available for code. Runners and models are configured per project stage and require installation and authentication. Tripo is used separately for 3D generation. Grok, GigaCode, Gemini and Qwen integrations are planned.
GrigDesk and project environments run on your machine. Cloud runners process the context you send at their provider. Chats can use local Ollama models.
Install GrigDesk and a runner, connect repositories, define check commands and prepare a preview environment. Then create a route in the editor. The guides take you through these steps in order.
Connect a project, choose a runner, and go from idea to acceptance.
Version 0.1. Project setup requires technical preparation. What to know →