Open infrastructure for cloud software factories

build on Warp: factories as code, any model or harness, with evals, benchmarks, and self-improvement built in.

request early accessdownload warp terminal
[ fig. 1 — the factory ]
[ fig. t4 · the factory ]8 × 28 · live
▩queued■working▨waiting□shipped

224 tasks · 0 active · 1,422 PRs shipped

Trusted by 800k+ devs at

AnthropicLivestreamOpenAILivestreamDockerCase StudyGoogleLaunch PartnerStanfordCourse PartnerPhantomRectangle HealthCase StudyGitHubAmazonAsanaNvidiaRetoolVMwareRampDoorDashPelotonTeamworks

Your software factory, defined in code.

Factories-as-code allows for a versioned and measured approach to optimizing costs and performance of your factories.

learn more
factory.yamlyaml
schemaVersion: v1alpha1name: web-server-factorydescription: Autonomous software-development factory for a web application.
alias: web-factoryThe alias is the Foreman’s @-mention handle in Slack and Linear, so teammates can route work to the Factory by name. It can differ from the Factory name.repositories: - owner: acme name: web-server - owner: acme name: web-clientRepositories define where Factory agents can work. Each run checks out the relevant code on its execution host so agents can inspect and change it.secrets: - DEPLOY_API_TOKENSecrets give agents protected credentials for the tools and services they need. Values are encrypted at rest and injected as environment variables only during runs.mcpServers: sentry: warpId: YOUR_MCP_SERVER_IDMCP servers connect every agent to shared tools such as Sentry or internal services. Each named connection references a centrally managed server.cloudProviders: aws: roleArn: arn:aws:iam::123456789012:role/factory-agentCloud providers securely connect Factory agents to cloud accounts and resources for infrastructure work. Federated access lets runs assume an AWS role or use a GCP identity without embedding long-lived cloud keys in the definition.integrations: - type: slack - type: linearIntegrations connect the Factory to work sources such as Slack and to Linear or Jira for task tracking, so the Foreman can coordinate work where your team already works.agentDefaults: model: auto runner: standardAgent defaults establish the model or harness, runner, and environment that roles inherit, while specialized agents can override those choices when needed.

Beyond CI/CD to automating the whole SDLC

defined in code, built for scale, and easy to deploy.

Baked-in measurement and self-improvement

evals, benchmarks, and self-improvement loops drive measurable gains.

[ fig. 4 · quality loop · sample run ]
[ fig. t5 · quality loop · sample run ]1 ink · scrub to read
EVALpass

Evals on your own work

96% 
100%50%0%apr 01may 01jun 01jul 01
8/13 07:03fail0.4
8/13 07:02pass0.8
8/13 07:02pass0.8
BENCHbest

Benchmarks across models

1.00x 
1.0x0.5x0xapr 01may 01jun 01jul 01
Claude Fable 5pass1.00x
GPT-5.6 Solpass0.94x
Gemini 3.6 Flashfail0.89x
LOOPauto-fix

Self-improvement loops

+3.7 
+4+20apr 01may 01jun 01jul 01
memory updatedpass+0.2
prompts tunedpass+3.2%
regression caughtfail-0.4

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.

read case study
[ WarpBench · benchmark results ]
Benchmark results comparing correctness against average cost across model configurations, with gpt-5.6-sol (high) called out as the benchmark winner at 95% correctness and $6.13 average cost.

Warp is enterprise ready

Run agents confidently with guardrails in place, centrally configured agent access, and centrally managed permissions.

  • Rectangle Health story cover

    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.

    read the story
  • Docker story cover

    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.

    read the story

Open at every layer

[ fig. 3 · open at every layer ]
Layer 01

Any agent

any MCP-capable coding agent.

  • warp
  • claude code
  • codex
  • cursor
Layer 02

Any model

frontier or open-weight, chosen per pipeline stage.

  • frontier
  • open-weight
Layer 03

Your compute or ours

warp's cloud, or self-hosted in your own VPC.

  • warp cloud
  • self-hosted
Layer 04

Data lives where you want

you own and store what your factory produces.

  • pluggable
  • zero-retention
  • your VPC

Control your coding agent chaos

continuous improvement, better governance and security, by default.

[ fig. 5 · control plane ]

increase agent roi · cost per pr

$—
computeplatforminference
[ fig. t6 · agents · live roster ]3 agents
ready for taskCODEXrnow
drafting the specCLAUDE CODEs14m
routed to specWARPt37m

Status advances on a shared clock; no agent is ever idle.

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.

Use Warp everywhere

Warp is an open agentic development platform that was built to work wherever and however you work.

  • Factories

    A software factory that automates and orchestrates software development.

    request access

  • Terminal

    An open-source terminal built for AI-assisted software development.

    Download Warp

  • Agent CLI

    A powerful coding agent that works in any terminal.

    curl -fsSL https://app.warp.dev/download/agent-cli | bash

Frequently asked questions

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 from triage through review to a mergeable PR.
as code, in a factory.yaml + supporting agent files. define triggers, agents, models, and approval gates — check it into your repo like any other config.
no. bring your own model or harness (e.g. claude code or codex) — warp factories works with whatever your team prefers and helps identify the most cost-effective configuration over time.
no. factories is a separate product — nobody at your company has to use warp terminal. work comes in through tools you already use, like slack, linear, jira, github, and gitlab. if you do use warp terminal, it has built-in factory integrations (native mcp) so you can iterate locally.
most orgs start around 20-30% of PRs fully automated, starting with simple tasks. over time this goes up as models improve and your factory self-improves.
wherever you choose — warp's cloud, or fully self-hosted inside your own VPC, under your existing retention and compliance rules.
humans put work into the factory via your existing tools like slack, teams, linear, jira, github and gitlab. at any time you can iterate on that work locally and the factory agents loop you in proactively when they need help.
yes — most teams start with a single low-risk workflow, like dependency bumps or flaky test triage, before expanding coverage.
usage-based, priced per agent run.