A team of agents on terminals you already pay for.
Sprints, backlog, and automations for the coding CLIs you already subscribe to — free, local, no new subscription.
Works with the terminals you already have
- Claude Code
- Codex
- Cursor
- Kimi Code
- OpenCode
- Grok Build
- Z.AI GLM
- Qwen Code
- OpenRouter
- + any Claude Code-compatible CLI
The mobile companion, live — try it.
Close the laptop. The run keeps going.
The phone is on the same run — answer the blocking question, steer the autonomy, and open the pull request from anywhere.
Review uncommitted workspace changes and manually test the feature.
48 files touched · 39 commands · 60 validation results
Open pull requestHow Sprint Engine works.
A plan becomes a graph
The architect splits a plan into tasks with dependencies, owners, and acceptance criteria.
The engine takes the wheel
Sprint Engine decides what unlocks, owns the concurrency, and drives first task to last.
Specialists run in parallel
The right specialist for each task, several tasks at a time.
Epic in, shipped work out
Hand it a whole-team epic; it runs to done, every step on the record.
What the work actually looks like.
Six columns — Todo, Ready, In Progress, In Review, Needs Input, Done — and a task’s column is derived from its dependencies, never dragged. Everything below came out of one markdown file, backlog/version-restore.md.
Needs you
Active
Recent
1 task is waiting on your answer. · 2 of 5 agents working · nothing merged yet
The board as the studio draws it — open a task, or answer the one waiting on you.
292 extensions, one click from any agent.
Curated MCP servers, skill packs, modules, and agent CLIs — each launches as an isolated chat or automation. Hand-picked from the HotStack index of 16,732 servers; the studio ships the curated set, not the index.
- Atlassian
- Brave Search
- Figma
- GitHub
- Grafana
- Linear
- Playwright
- Notion
- OpenAI Docs
- Railway
- Sentry
- Stripe
- Supabase
- Context7
- Vercel
- API Reference MCP
- Browser Automation MCP
- Current Docs MCP
- Repository Workflows MCP
- Dead code sweep
- Duplication review
- Unit test coverage
- UI & UX review
- Merged-PR seam review
- 42crunch-api-security-testing
- astronomer-data-agents
- code-review
- firebase
- mcp-tunnels
- prisma
- slack
- aws-dev-toolkit
- datarobot-agent-skills
- oracledb
- monday-crm
- rootly
- idmp-plugin
Marketplace
On this machine
AtlassianJira, Confluence, and Compass search, summarization, issue, and page workflows.
Brave SearchLive web, local, news, image, video, and LLM-context search through Brave Search.
FigmaDesign context, variables, components, Code Connect, and write-to-canvas workflows.
GitHubRepository, issue, pull request, Actions, release, and code security workflows.
GrafanaMetrics, logs, dashboards, incidents, and alerting context from Grafana.
LinearIssue, project, comment, team, and roadmap workflows for Linear.- PlaywrightBrowser automation for inspecting pages, driving UI flows, and validating web app behavior.
NotionWorkspace page, database, comment, and team knowledge workflows in Notion.- OpenAI DocsOfficial OpenAI documentation lookup for API, Codex, and ChatGPT integration work.
RailwayProject, service, deployment, environment, variable, and domain management for Railway.
SentryProduction error, trace, performance, and release investigation through Sentry.
StripeStripe API and knowledge-base access for payments, billing, customers, and subscriptions.
SupabaseProject-scoped Supabase database, auth, storage, functions, and documentation workflows.- Context7Developer documentation lookup for libraries and frameworks.
VercelProject, deployment, log, and team context for Vercel-hosted applications.
API Reference MCPInstalls the official OpenAI Docs MCP endpoint for API, Codex, and ChatGPT integration lookup.
Browser Automation MCPInstalls the Playwright MCP server for browser inspection, UI automation, and end-to-end debugging.
Current Docs MCPInstalls the Context7 MCP server for current library documentation lookup.
Repository Workflows MCPInstalls the GitHub remote MCP endpoint for repository, pull request, and Actions workflows.
Extensions as it opens in the studio — add one and the counts follow.
The workspace you build yourself.
Every surface is a module and the SDK is public. This calendar is the benchmark: a full workspace built against the published SDK, outside our own repo.
Built on the Module SDK
Signed, verified, and installed like any first-party module — the same surface our own panels are built on.
First-class session manager
Your workspace spawns real agent sessions through the shared runtime.
Extensions and sprints included
Drop an automation on a calendar cell and it fires a real agent at that time.
Your backlog, live
Watch items in real time and hand back deep links.
Simulated — watch an agent assemble the workspace, then drag a backlog card onto the grid.
Review catches real problems.
From 136 sprint runs of the projects that build SprintEngine itself. See the full breakdown →
Explore the studio.
From the workshop.
All posts →Common questions.
- Is SprintEngine Studio another AI IDE?
- No — it is the local environment around your agents: terminals, files, Git, workspaces, extensions, and a knowledge graph.
- Where does my code go?
- Nowhere — it's a local desktop app. The only network calls are the ones your CLI agents already make.
- Do I need a new AI subscription?
- No — that's the point. If your terminal can run it, the studio can orchestrate it.
- Can we build our own modules?
- Yes — workspace types, providers, skills, and MCPs are all plugin surfaces, and the marketplace is the distribution path.
Download SprintEngine Studio.
Free — bring the subscriptions you already have.