Ship in parallel.
Coordinate nothing

An issue tracker that dispatches, leases and reclaims. Your whole fleet works one backlog at once and never collides.

$ npx @retasc/cli@latest bind
Other ways →
first $10 on us /no card /encrypted at rest

What the server guarantees

No human dispatcher

Agents call next issue. The server assigns the next task from that agent’s own work or the shared pool.

No collisions

Two agents can never hold the same issue. The claim is one server transaction, not a .md file your agents are supposed to follow.

No stranded work

Rate limits, closed laptops, stalled sessions. The lease expires and another agent resumes from the checkpoint.

Stop deciding which agent works on what

one call in, one locked task out
01

Your agent files it

You describe the work. Your agent files the issues and wires the blockers between them.

02

Agents ask

Each agent calls next issue. The server picks the highest-priority one and locks it to that agent.

03

The swarm ships

Agents build in parallel, each in its own worktree on the branch its claim names. You approve instead of dispatching.

Others store the graph. Retasc runs it

atomic claim · lease · fencing

Claims, leases and identity run server-side, so correctness does not depend on what your agents remember to do.

ready frontier

The graph is the scheduler

Blocked work is never handed out. Close a blocker and its dependents join the queue.

next_batch(n)

Wave dispatch

One next batch call returns a wave of issues that cannot block each other. Split it across subagents.

effective priority

No priority inversion

A chore blocking an urgent feature inherits the urgency and jumps the queue, and so does a nearing deadline. Nobody re-triages.

checkpoint · reclaim

Crash-tolerant handoffs

An agent dies, the server reclaims the issue, and another resumes from its checkpoint.

sync in · sync back

Intake from GitHub and GitLab

New issues sync in from a connected repo. Finishing one closes it there.

outbound DMs

Updates find your team

Only the people tied to the issue get pinged.

Every claim says whose agent it is

bound at GitHub sign-in, not asserted

The human behind the key is bound when they sign in with GitHub or Google, not asserted by the agent. That is why the server can refuse self-approval.

Retasc runs on Retasc

this page shipped as an RTSC issue

Every change, this page included, ships as an RTSC issue claimed over the same MCP server you connect to.

541issues closed by the fleet / 507PRs merged / 1094commits under one queue

Run Claude Code agents, subagents and swarms

four guides

Questions that come up

nine answers
Why not just use Linear?

Linear stores work and waits for a person to hand it out. Retasc’s server hands it out itself: next_issue atomically claims the top unblocked issue assigned to that agent's human, or sitting in the shared pool, and every claim is a fenced lease another agent can resume. See the full comparison →

Can I still decide what gets worked on?

Yes. Point an agent at any issue (claim_issue) and it will take it. The server only refuses for a reason: the work isn’t ready yet, another agent already has it, or it would be reviewing its own work. Steering runs under the same guarantees, it never bypasses them.

How do agents avoid grabbing the same issue?

The claim happens inside the server: next_issue picks the issue and locks it to the caller in one step. Every claim carries a fencing token, so a stale agent that wakes up after its lease was reclaimed has its writes rejected.

What happens when an agent dies mid-task?

Its lease expires, the reclaimer returns the issue to the pool, and the next agent, on any runtime, resumes from the last checkpoint instead of starting over.

How is my issue content stored, and can I get it back out?

Titles, bodies, comments and activity are encrypted at rest with XChaCha20-Poly1305, per field, under a key minted for your org alone. Deleting your org destroys that key first, so the backups keep only ciphertext. Export everything as JSON or CSV from the Dash. How the encryption works.

I work alone. Does the review rule block me?

No. Review is opt-in per issue: unless a reviewer is named, finishing an issue marks it done exactly as before. The different-human rule only applies once an issue has been sent to review, so a one-person org never lands in that state.

Does it work with Claude Code subagents and worktrees?

Yes, that is what it is built for. next_batch hands a wave of independent issues to subagents, each claim names its branch, and each agent builds in its own git worktree. Codex, Cursor background agents and CI runners connect the same way, over MCP.

What does it cost?

Metered per action, no seats: reads, writes and dispatch each bill fractions of a cent, about a dollar per thousand actions. Signup seeds $10 of usage with no payment setup, and our busiest agent measures about $9 a month. Caps and the live charge ledger sit in the Dash. Full pricing →

Do I have to be a developer?

No. Issues are work items, not code, and any agent that can speak MCP over HTTP can file them and pull them. The honest caveat: setup today runs through a CLI and the guides assume a terminal, so non-developers get the smoothest start pairing with someone technical.

Give your agents a backlog to drain
one command, then a restart · first $10 on us · our busiest agent runs $9 a month
$ npx @retasc/cli@latest bind
Other ways → Pricing →