Warp — The Open Platform for Automating Development
_[ fig. 1 — the factory ]⌗
live
factory.yaml applied to all 112 agents
# factory.yaml
schemaVersion: v1alpha1
name: acme-web
repositories:
- owner: acme
name: web
mcpServers:
github:
warpId: mcp_github
agentDefaults:
model: claude-5-fable-high
SDLC coverage
Beyond CI/CD to automating the whole SDLC
defined in code, built for scale, and easy to deploy.
opinionated, but flexible
set up your first factory in 5 minutes, build it out over time.
_[ fig. 2 · quickstart ]⌗
factories as code
repos, agents, models, permissions, and checkpoints in one definition.
_[ fig. 2 · factory.yaml ]⌗
# factory.yaml — factories as code
schemaVersion: v1alpha1
name: pr-review
repositories:
- owner: acme
name: web
agentDefaults:
model: claude-5-fable-high
# agents/foreman/agent.md
agentType: FOREMAN
# agents/review/agent.md
agentType: REVIEW
model: glm-5.2-fireworks
# automations/on-pr/automation.md
agent: review
triggers:
- provider: github
event: pull_request_ready
API, CLI, SDK and MCP
built as a platform, not a vertical product or AI teammate.
_[ fig. 2 · API / CLI / SDK / MCP ]⌗
# cli
$ warp agent run-cloud --environment ENV_ID \
--prompt "fix LIN-482, low risk only"
# api
$ curl -X POST https://app.warp.dev/api/v1/agent/runs \
-H "Authorization: Bearer $WARP_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "prompt": "fix LIN-482" }'
{ "run_id": "run_4026", "state": "QUEUED" }
# sdk (typescript)
const run = await client.agent.run({ prompt: 'fix LIN-482' });
console.log(run.run_id);
# mcp · warp-factory server
{ "tool": "send_task", "factory_uid": "fct_acme_web",
"title": "Fix LIN-482", "note": "low risk only" }
integrations
work flows in from chat, tickets, and source control; status flows back to where it started.
any surface
watch, steer, and hand off runs from web, mobile, terminal, or IDE.
evals, self-improvement, and memory
every run is scored; observer agents open PRs against your factory config to improve it.
quality loop
Baked-in measurement and self-improvement
evals, benchmarks, and self-improvement loops drive measurable gains.
evals on your own work
pass 96%
100%50%0% apr 01 may 01 jun 01 jul 01
benchmarks across models
best 1.00x
self-improvement loops
auto-fix +3.7
case study
Cutting our cost per PR from $80 to $30
How we used Warp Factories Benchmarks to test models on our own engineering tasks and optimize for cost without sacrificing quality.
Warp is enterprise ready
Run agents confidently with guardrails in place, centrally configured agent access, and centrally managed permissions.
Rectangle Health uses Warp to build a self-improving AI teammate
Rectangle Health turned a senior engineer's side project into Rex, a self-improving AI teammate built on Oz that now writes 54% of its own code.
Docker uses Warp to reduce onboarding time and give every engineer a shared source of truth
Docker adopted Warp for a more user-friendly terminal experience, using Warp Drive to streamline repetitive workflows and boost team productivity.
no lock-in
Open at every layer
_[ fig. 3 · open at every layer ]⌗
Any agent
any MCP-capable coding agent.
Any model
frontier or open-weight, chosen per pipeline stage.
Your compute or ours
warp's cloud, or self-hosted in your own VPC.
Data lives where you want
you own and store what your factory produces.
governance
Control your coding agent chaos
continuous improvement, better governance and security, by default.
_[ fig. 5 · control plane ]⌗
increase agent roi · cost per pr
$18.09 -33% may 20
one control plane for every agent
resolve merge conflicts on server
agents prove their work with computer use
every factory agent captures a screenshot or video so you can verify its work before shipping a PR.
Frequently asked questions
what is a cloud software factory?
a factory is a fleet of agents wired to your SDLC — triggered by an issue, a slack message, or a schedule, and coordinated by warp factories.
how do i define a factory?
as code, in a factory.yaml + supporting agent files.
do i have to use warp's models or config?
no. bring your own model or harness (e.g. claude code or codex).
do i need warp terminal to use factories?
no. factories is a separate product.
how much of my SDLC can be automated?
most orgs start around 20-30% of PRs fully automated.
where does our data live?
wherever you choose — warp's cloud, or fully self-hosted.
how do humans interact with the factory?
humans put work into the factory via your existing tools.
can we start small?
yes — most teams start with a single low-risk workflow.
what does it cost?
usage-based, priced per agent run.