Project setup and continuity for your coding agent

Give your codingagent a clearnext step

Turn your plan into a task queue your coding agent can follow. Set up project context, track what is in progress, and pick up where you left off through CLI or MCP. Start locally without an account; hosted features have separate access requirements.

Advanced multi-agent capabilities remain preview or not-live; check each feature's availability.

Start locally Read the docs

Works with your coding agent
A shared project plan
Persistent task progress

Install in one line

npm i -g @girardmedia/bootspring && bootspring init

bootspring · build loopEXAMPLE

$ bootspring build next
›Example task: add a project settings page
›Read the acceptance criteria in planning/TODO.md
›Your coding agent implements the task
$ npm test
›Review the actual test results before completing
$ bootspring build status
›Check progress, then continue from the active task

Runs where your agents already work

Claude Code
Codex
Gemini CLI
Cursor
VS Code
Antigravity
Windsurf
Continue
OpenCode
Aider
Claude Code
Codex
Gemini CLI
Cursor
VS Code
Antigravity
Windsurf
Continue
OpenCode
Aider

Golden path

From project plan to your next completed task

Keep the project plan and task progress alongside your code, accessible to the coding host you already use.

Prepare the project

Capture the goal, tasks, and acceptance criteria in your project plan so your coding agent has a clear definition of the work.

bootspring seed

Run the build loop

Select a task through CLI or MCP. Your coding agent makes the changes; run the project checks and review the result before completing it.

bootspring build next → done

Continue with context

Check the active task and saved progress when you return. Hosted account features are available separately from your local build workflow.

bootspring build status

Start free Read the build loop docs

What actually ships

A control plane, not another autocomplete.

Cursor, Copilot, and Claude Code write code. Bootspring governs the work: queue, ownership, proof, and the dashboard that keeps the team aligned.

SHIP

CLI + MCP build loop

bootspring build next / done against a dependency-aware queue. Local MCP tools for Claude Code, Codex, and hosts that speak MCP.

SHIP

todo.md as contract

Visible tasks, ownership, and handoffs. Agents and humans share one source of truth.

SHIP

Hosted control plane

Projects, API keys, billing, devices, and support on bootspring.com — the product surface operators actually use.

TRUST

Honest claim labels

Live vs preview vs not-configured stays visible. We market what ships — swarm and lab AI stay labeled until runtime proof.

PREVIEW

Agent-ready, not agent-theater

Slots, leases, and conflict scans for multiplayer builds. Parallel agents are illustrated with real mechanics — not fake green status.

SHIP

Quality gates first

Run your project checks before marking work done. Review handoffs, receipts, and actual test results before continuing.