The agent runtime for shipping software

Assign the issue. Drisp ships.

Assign an issue to Drisp and it takes it from there — self-transitioning every status and running the right workflow on Drisp Cloud. Build, review, QA on a live browser, all the way to Done. You set direction. It does the work.

Open source · MIT-licensed CLIRuns on Claude Code or Codex

issue tracker · assign to drisp
Backlog
ENG-482

Add SSO to the dashboard

authDrisp
ENG-501

Rate-limit the public API

backendSL
ENG-498

Dark-mode polish pass

frontendMR
ENG-510

GraphQL schema cleanup

backendJK
ENG-512

Flaky e2e on CI

infraDV
In Progress
ENG-489

Stripe webhook idempotency

backendJK
ENG-455

Audit-log export

backendSL
In Review
ENG-477

Webhook delivery retries

backendJK
ENG-468

Cursor pagination

apiMR
ENG-460

OAuth token refresh

backendSL
QA
ENG-471

Mobile nav regressions

frontendDV
ENG-466

Empty-state polish

frontendSL
Done
ENG-462

Self-serve billing portal

featureMR
ENG-459

Invite teammates

featureJK
ENG-448

CSV import limits

featureDV
Runs on
Claude CodeOpenAI Codex
Assign from
LinearJiraGitHubNotion
01 / the problem
The problem

The agent is fine.
The workflow around it is broken.

  • Same prompt. Same model. Different output every time.
  • Agents drift over long runs. No checkpoints, no way to recover.
  • What works for one dev doesn’t transfer to the team.
  • You see the final output. Not the 40 tool calls that produced it.
  • Agent tooling assumes a human at the keyboard. CI and automation are afterthoughts.
  • One agent at a time. Engineering caps at what a single developer can babysit.
The fix

One runtime.
Local or cloud. One agent or a thousand. Same definition, same result.

Drisp sits between you and the agent. Define steps, constraints, and exit criteria once. Run on Claude Code, Codex, or any future agent runtime. Locally, on your own infra, or fanned out across Drisp Cloud.

01
Structure over prompting
Define jobs declaratively. Steps, constraints, exit criteria. Not conversationally.
02
Checkpoints, not hope
Every step is verifiable, every run is resumable. No silent drift.
03
Team-portable
What one developer builds transfers to the whole team. Same workflow, same result.
04
Parallel by default
One workflow runs once or a thousand times. Same definition, no rewrite. Scale is a dial.
05
Pipeline-first
Built for CI from day one. Not interactive-first, retrofitted later.
02 / built for parallelism

Spawn agents
in parallel.

A workflow is a unit of agent work. Drisp turns it into something you run once, ten times, or a thousand times. Across one runner or many. Same definition. No rewrite.

01

One agent

A single workflow on a single repo. Your laptop, your CI job, your local agent. The starting point everyone knows.

02

Ten agents

Fan out across a sprint of tickets, a feature's full test matrix, or a fleet of microservices. One workflow definition, ten parallel runs, one aggregated result.

03

A thousand agents

Drisp Cloud spins up runners on demand. Treat coding agents as horizontal capacity. Same workflow, factory-scale throughput, structured artifacts piped back into the rest of your pipeline.

Triggered from a webhook, a schedule, or a single CLI command. The workflow doesn’t change as you scale. The runtime does.

03 / one runtime, two operators

One runtime.
Two operators.

The Drisp CLI is the runtime. It sits on top of Claude Code or Codex and coordinates every step of every workflow. Run it yourself, or attach it to a managed runner on Drisp Cloud.

Open source

Drisp CLI
Run it yourself.

MIT-licensed CLI. Install it on your laptop, run it in CI, or self-host it on your own infrastructure. Bring your own agent keys. Own your data.

$ npm install -g @drisp/cli
$ drisp workflow install playwright-automation
$ drisp --workflow=playwright-automation
  • Free, forever
  • Local-first dev loop
  • Self-host on any container runtime
  • Workflows install from the marketplace or from a local path
Recommended for teams

Drisp Cloud
Let us run it for you.

Spin up a managed runner from the dashboard, attach the workflows it should run, and trigger it from anywhere. Same CLI underneath. Drisp Cloud handles the infra, schedules, queues, retries, checkpoints, and storage.

drisp.cloud → New runner → Attach workflow → Save
  • Free to start — no card required
  • Pay per run after that
  • Triggers from GitHub, cron, REST, Slack, or webhook
  • SSO, audit log, role-based access for teams

Workflows are the same in both modes. Whether you type drisp workflow install on your laptop or attach a workflow to a Cloud runner from the dashboard, the same install runs underneath.

04 / workflow marketplace

Install workflows
like packages.

Browse community-maintained workflows or publish your own. Each one is scoped, tested, and version-pinned. Install with a single command on the CLI, or attach one to a Cloud runner.

playwright-automation

v0.0.21
lespaceman/athena-workflow-marketplace

Writes, reviews, and stabilizes Playwright end-to-end tests from live product flows.

$ drisp workflow install playwright-automation
Coverage plansTest implementationFlaky-test fixes

robot-automation

v0.0.21
lespaceman/athena-workflow-marketplace

Generates Robot Framework suites with reusable keywords, structured fixtures, and CI-ready runs.

$ drisp workflow install robot-automation
Keyword librariesSuite scaffoldingCI integration

exploratory-testing

v0.0.14
lespaceman/athena-workflow-marketplace

Runs charter-based exploratory sessions, captures evidence, and files actionable issues.

$ drisp workflow install exploratory-testing
Session chartersEvidence captureTriage-ready reports

smoke-testing

v0.0.14
lespaceman/athena-workflow-marketplace

Defines and executes smoke suites against critical paths so breakages surface before release.

$ drisp workflow install smoke-testing
Critical-path mapPre-release smoke runPass/fail summary

regression-testing

v0.0.14
lespaceman/athena-workflow-marketplace

Scopes impact-based regression runs, reruns the right areas, and reports deltas against the last release.

$ drisp workflow install regression-testing
Impact-based scopeRerun depth planRelease-over-release diff

fullstack-engineering

v0.0.9
lespaceman/athena-workflow-marketplace

Maps the codebase, implements the change, validates the result, and ships a PR for full-stack features and fixes.

$ drisp workflow install fullstack-engineering
Codebase mapPhased implementationValidated PR
05 / how it works

Assign, walk, ship.

Three steps. Assign the issue, Drisp walks the statuses, it ships to Done. You stay out of the loop until it needs you.

01. Assign the issue

Assign it like a teammate.

Assign an issue to Drisp in Linear, Jira, GitHub, or Notion. That is the one human action — no workflow to pick, no command to run.

◆ ENG-482 assigned to Drisp
✓ picked up · Add SSO to the dashboard

Assignment is the primary trigger. Cron, REST, Slack, and webhook work too.

02. Drisp walks the statuses

It self-transitions each status.

Drisp moves the issue In Progress → In Review → QA → Done, fanning out the right workflow per status across Cloud runners.

$ status → In Progress
▸ tdd-fullstack ×3 | running
▸ playwright ×14 | QA

On Drisp Cloud: each workflow runs on managed runners with queues, retries, and storage handled.

03. Ships to Done

Shipped to Done.

PR merged, 0 regressions, issue closed. Most issues ship hands-off; some loop a human in, and auto-merge is an opt-in ceiling.

✓ PR #482 merged
✓ 0 regressions
✓ ENG-482 → Done

~80% of issues ship hands-off. ~20% pull a human in. You stay in control of the merge.

06 / capabilities

Specialized workflows.
Spawned at scale.

Pre-built agent programs for the work engineers actually ship. Dispatched from the surfaces your team already uses, fanned out across as many runners as the job needs.

Prebuilt for real work.

Pre-built agent programs for QA, security, code review, frontend, full-stack, and devops. Install once. Dispatch when needed.

Assign in your tracker.

Assign an issue in Linear, Jira, GitHub, or Notion and Drisp picks it up — the one human action. Cron, REST API, Slack, and webhook trigger runs too.

Claude Code or Codex.

Write a workflow once and run it on either harness. Drisp normalizes the event stream, so the same definition, plugins, and logs work on both.

Debuggable logs.

Streaming events, tool calls, tokens, cost. When a run fails, you see exactly where and why. At one agent, or at a thousand.

Drisp CLI is free, forever. Drisp Cloud is free to start, then pay-per-run for managed runners, so cost scales with the work, not with the seat count.

See pricing →

Toward the autonomous engineering factory.

Workflows as labor. Runners as workforce. Scale as a dial. Drisp is the standard the rest is built on. We’re shipping it one workflow at a time.

Drisp

Start building.

Install the CLI and run your first workflow locally. Or sign up for Drisp Cloud and spawn agents at scale.

$ npm install -g @drisp/cli