Product management that lives in your repo specs
Specboards is product management for teams building with spec-driven agentic development. It layers status, priority, roadmap, and ownership on the spec files your team and your AI coding agents already commit to your repo, with no duplication into Jira or Aha.
Specboards is in pre-release. Access is invite-only while we onboard product teams.
Specs stay canonical in git, versioned with your code and read by AI coding agents.
Add product metadata on top. No copying specs into Jira or Aha.
One source of truth for product, UX, engineering, and the agents building alongside them.
Features
Everything a product team needs to run on specs
The planning layer for spec-driven development, without pulling specs out of git.
Git-native specs
Your specs/**/spec.md files stay the source of truth. Specboards parses each spec, injects a stable UUID when one is missing, and keeps a live, sha-tracked index. Renames and moves never orphan your data, because every spec is keyed by its id, not its path.
Ideas & intake
Capture raw ideas and requests in a dedicated Ideas view, then promote the ones worth doing straight into the backlog as specs. Nothing gets lost between feedback and the plan.
Backlog & prioritization
Rank, assign, tag, and prioritize work items in a fast backlog. Drag to reorder, save custom views, and filter by product, status, or owner.
Kanban board
A status board with a validated workflow: backlog, defining, ready, in progress, in review, done, plus archived. Status always means the same thing, and each repo can customize the stages and transitions in .specboards/config.yml.
Roadmap
Group work into initiatives and epics, then lay it out by release and quarter. Communicate the plan, and what ships when, without spreadsheets or a second tool.
Releases
Bundle work into releases with a status and target date, and track what ships when. Roadmap and MCP both read them, so your team and your agents share one view of what's next.
One-click GitHub sync
Connect a repo with a one-click GitHub App. Specboards imports specs, reconciles changed specs on every push, and links live PR, issue, and branch state to your work.
MCP for AI agents
An MCP server exposes your prioritized, assigned, status-aware backlog to coding agents. They can list products and items, read specs, follow dependencies, update status and metadata, and even write specs back to git (list_items, read_item, update_item, create_spec), so agents work from the same plan your team does.
Why not just use...
You already have the specs. You're missing the layer on top.
If your team is adopting spec-driven agentic development, the specs already exist. Specboards doesn't replace them or move them into another tool. It adds the product-management layer around the specs in your repo.
Why not just use Jira or Aha?
Product lives in a separate system of record. Every spec has to be copied out of the repo and kept in sync by hand, so the plan and the code drift apart.
With Specboards: The spec files in your repo stay canonical. Specboards layers status, priority, and roadmap on top, so there's nothing to duplicate and nothing to reconcile.
Why not just use Linear?
Great for issues, but the actual specification still lives somewhere else - a doc, a wiki, a ticket description - away from the code and invisible to your AI agents.
With Specboards: Your specs are the work items. They're versioned with the code and readable by coding agents over MCP, so people and agents plan from exactly the same source.
Why not just use Notion or Confluence?
Specs drift from the code the moment they're written, there's no real status workflow across them, and nothing is machine-readable for an AI agent to act on.
With Specboards: Specs move through a validated status workflow, ship inside pull requests with the code, and expose a structured, agent-readable backlog.
Why not just use Plain markdown in git?
You get canonical specs but no layer on top: no status, no priority, no ownership, no roadmap, and no board to see it all across features.
With Specboards: Keep the markdown exactly where it is. Specboards adds the backlog, board, roadmap, releases, and ownership around it, without pulling it out of the repo.
How it works
From repo to roadmap in minutes
No migration project. Point Specboards at a repo and your specs become a managed backlog.
Connect your repo
Set up the GitHub App in one click. There are no secrets to paste; credentials are created and stored encrypted for you.
Specs import automatically
Specboards scans specs/** per your .specboards/config.yml, homes each under a Feature, and keeps the index in sync on every push.
Plan, track, and ship
Work the Ideas, Backlog, Board, and Roadmap in the app. Your AI agents read the same prioritized plan over MCP.
Ecosystem
Works with the spec-driven tools you already use
Specboards reads plain markdown specs in git. Whether your team writes specs by hand or generates them with Spec Kit, Kiro, or OpenSpec, Specboards turns them into a managed backlog.
GitHub Spec Kit
Spec Kit's /specify workflow writes specs/<feature>/spec.md straight into your repo. Specboards indexes those same files, so every Spec Kit feature lands on your backlog and board automatically.
Kiro
Kiro's spec sessions turn prompts into requirements and design docs that live with your code. Specboards layers status, priority, ownership, and roadmap over the specs your Kiro workflow produces.
OpenSpec
OpenSpec keeps change proposals and specs in git as markdown. Point Specboards at the repo and those artifacts get a product home: ranked, owned, and scheduled into releases.
Claude Code, Cursor & MCP agents
Any coding agent that speaks the Model Context Protocol can read your prioritized backlog, update status, and write specs back to git. Your agents plan from the same board your product team does.
New to the practice? Read our guide to spec-driven development, including core material from GitHub, Anthropic, OpenAI, and AWS.
Open core
Yours to run, or hosted by us
The core is Apache-2.0. Self-host for internal control, or use the managed SaaS and skip the ops.
Self-host
The full web app, hosted MCP endpoint, and GitHub sync run from one Docker Compose stack (the web image plus Postgres). No feature gates on the core.
Get the codeHosted SaaS
Request access to the hosted beta, then connect a repo in minutes. We run the database, deploys, and updates so your team can focus on the product.
Request accessFAQ
Spec-driven development, answered
Common questions about spec-driven agentic development and where Specboards fits.
What is spec-driven development?
Spec-driven development is a workflow where a written specification, usually a markdown file committed to the repo, is the source of truth for what gets built. Tools like GitHub Spec Kit, Kiro, and OpenSpec help teams author and refine those specs, and AI coding agents implement against them. The spec, not the ticket, drives the work.
Where does product management fit into spec-driven development?
Specs describe what to build, but product teams still have to decide what to build next, who owns it, and when it ships. Specboards adds that layer directly on the spec files in git: ideas and intake, a prioritized backlog, a kanban board, a roadmap, and releases, with no separate tracker to keep in sync.
Who is Specboards for?
Product teams adopting or already building with spec-driven agentic development: product managers who need a backlog and roadmap, engineers who want specs to stay canonical in git, and teams pairing with AI coding agents that read and write those specs.
Does Specboards work with GitHub Spec Kit and other spec tools?
Yes. Specboards indexes plain markdown specs in your repo (specs/**/spec.md by default, configurable per repo in .specboards/config.yml). Specs authored with Spec Kit, Kiro, OpenSpec, or by hand all work the same way.
How do AI coding agents use Specboards?
Through Specboards' built-in MCP server. Agents like Claude Code and Cursor can list products and work items, read specs, follow dependencies, update status and metadata, and create new specs in git, so they work from the same prioritized plan as your team.
Is Specboards open source?
The core is open source under Apache-2.0, with no feature gates: the full web app, MCP endpoint, and GitHub sync run from one Docker Compose stack. You can self-host it, or request access to the hosted SaaS and skip the ops.
Bring product management to spec-driven development
Request access, connect a repo, and put your backlog, board, and roadmap where your team and your agents already work: the specs in git.