Where your projects and your agents meet.
Three layers that work as one.
Workspace
A beautiful home for your projects.
Worth running on its own
Kanban · file system · notes & more
MCP layer
The bridge between your workspace and your personal agents.
ChatGPT · Claude · Gemini · any MCP app
Runner harness
Assign AI roles to automate your workspace, exactly as the project needs.
Backend-authoritative
Quickstart
Three steps to a self-driving workspace.
Stand up the platform, hand your agent the MCP keys, and point a runner at your board. Self-host it, or skip the setup with Valaris Backplane Cloud.
npx valaris-backplane initQuickstartThe one-command bootstrap is on the near-term roadmap. Today you self-host from the repository — full steps in the docs.
1 · Launch the platform
Boards, notes, resources, and project definitions — a workspace your whole team can run with zero agents.
2 · Connect the MCP layer
Add the Valaris MCP server to Claude, Codex, or any MCP-capable agent with one personal API key.
3 · Deploy a runner
Aim a runner at your board and let role-based pipelines carry cards from backlog to merged.
Three layers, one platform
Adopt exactly as much power as you need.
Each layer stands on its own and compounds with the next. Start with a workspace, hand it to your agents, then let runners take the wheel — at your pace.
Layer 1 · The Platform
A delivery workspace your team will actually open.
Plan, document, and track work in one place — polished and fully usable before a single agent shows up.
Boards
Kanban with typed cards, priorities, labels, due dates, participants, and dependencies. Drag between lanes with instant optimistic updates; filter and search by status, priority, type, assignee, and label.
Notes
Rich-text notes for decisions and working context. Pin them, link them to cards, scope them to one board or the whole workspace.
Resources
A per-workspace file tree with folders, tags, and in-browser previews for images, PDFs, video, CSV, markdown, and code — access-isolated per workspace.
Definitions
One structured spec per board: scope, objectives, milestones, tech stack, stakeholders, constraints, and key decisions.
Rate-limit the export API
Audit log retention
Refactor auth middleware
Fix flaky upload test
Signed URL rotation
Layer 2 · A native MCP server
Hand your agent the keys to the workspace.
The Valaris MCP server is native to the platform and speaks standard Model Context Protocol — so it works with any MCP-capable agent, never just one vendor.
Read and write boards, cards, columns, notes, definitions, and resources
Pull project context, board health, and dependency status on demand
Connect Claude, Codex, or anything that speaks MCP
Authenticate with a personal API key minted from your settings
Tools and resources work with any compliant MCP client. A published one-line installer is on the roadmap — today you point the config at the repo.
{
"mcpServers": {
"valaris": {
"command": "bash",
"args": ["mcp-server/run.sh"],
"env": {
"VALARIS_API_URL": "https://your-workspace",
"VALARIS_API_KEY": "vlr_…"
}
}
}
}Layer 3 · Runners
Push what one LLM agent can reliably finish.
Runners are a backend-authoritative harness: the platform owns the roles, the rules, and the context. The agent does the work — deterministically steered toward the goal.
Roles
Built-in roles — orchestrator, reviewer, documentator, researcher, planner — plus any custom role you define. Each is one stage of a pipeline.And because a role is just configuration, it's shareable by design.
Lifecycle steps
Compose behavior from 19 deterministic step kinds — discover, claim, git, LLM, sensors, move card, open PR, merge, and more — with branching and on-failure routing.
Context sources
Feed each role smart, pre-processed context: sibling cards, board definitions, notes, dependency health, execution history — even the pipeline's own config.
Sensors
Computational quality gates — run tests, catch merge conflicts, flag overlapping PRs — that route the pipeline on pass or fail.
Configurability
With great configurability comes great responsibility.
Tune any step of any role, write precise directives, chain hooks. That power cuts both ways — thoughtful configuration produces results you haven't seen before; careless configuration burns budget and misguides agents. We build the guardrails so you can push the limits without falling off them.
Observability
Know what every run costs. Trace every move it made.
Cost is attributed per execution, role, card, and model. Set a lifetime budget per runner and a per-workspace cost circuit breaker that alerts, pauses, or stops work before the bill surprises you.
Cost tracking
Per execution, role, card, and model.
Budgets
Per-runner caps and a per-workspace circuit breaker.
Traceability
A full record of every run, tool call, and card touched.
See it in motion
The platform, before a single agent runs.
Boards, cards, project definitions, and notes — a real workspace tour, captured from the live product.
Open source & cloud
Run it yourself, or let us run it for you.
Valaris Backplane ships as an open-source platform you fully control — with a managed cloud for teams who'd rather not operate it.
Open Source
Run the whole platform on your own infrastructure. Own the data, extend any layer, audit every line.
- Full platform, MCP server & runner
- Your infrastructure, your data
- Extensible and inspectable
Valaris Backplane Cloud
We host the platform and handle the ops, so your team ships instead of babysitting infrastructure.
- Hosted platform & runners
- Support and onboarding
- Scales with your team
FAQ
Questions, answered.
No. The platform — boards, notes, resources, and definitions — is fully usable by people alone. The MCP layer and runners are upgrades you switch on when you want them.
Start with a workspace. Grow into a pipeline.
Self-host the open-source platform today, or request access to Valaris Backplane Cloud — your call.
npx valaris-backplane init