Back to vendors
W

Warp

Also known as: Warp Oz

Visit site
Entry priceFree, then Build at $20 a month ($18 a month billed annually).Full pricing detail

Agentic development environment born out of the terminal, pairing an open source Rust client with Oz cloud agents and Warp Factories. Factories, in early access, runs fleets of coding agents across the SDLC, defined as code, on any model or harness, with approval gates and audit trails for each tool call.

Warp is an agentic development environment that grew out of the terminal. Built from scratch in Rust for speed, it began as a modern terminal accelerated by the GPU and has been rebuilt around AI agents. Its premise is that a large share of real engineering work, from DevOps and deployment to debugging and data operations, happens in a shell, not an editor, and deserves full agent support there. It runs on macOS, Windows and Linux. Warp has open sourced its core client under dual MIT and AGPL v3 licensing, with OpenAI as flagship sponsor of the repository.

The terminal's defining idea is the block. Every command produces its own block holding the command, its output, exit code and duration. You can select, filter, bookmark and share a block instead of scrolling through a wall of text. On top of this sits an input that works like an IDE, with completions, syntax highlighting and prediction of the next command.

Warp Terminal is the client. Warp Agent CLI is a coding agent that runs in any terminal. Oz cloud agents run on the Automation Platform, where a parent agent can spawn and coordinate child agents, and runs start from schedules, CI events, Slack, Linear, Jira or the Oz API.

Warp Factories, in closed early access, is open infrastructure for building a cloud software factory: a fleet of agents wired to the SDLC and defined as code in a factory.yaml that names repositories, agents, models, permissions and checkpoints. A foreman agent moves each task down a six stage line of triage, spec, implement, verify, ship and monitor. It stops at whichever human gates the team configures, and merge always stays with the customer.

Warp leaves the choice of what runs underneath to the customer. Teams pick among Fable 5, Claude Opus 5, GPT-5.6, Gemini 3.1 Pro, GLM 5.2, Kimi K3 and others, and can run different tasks on different models in parallel. They can bring their own API keys on any plan (companies over ten employees need Business or Enterprise for that) or route inference through their own cloud on Enterprise. External CLI agents including Claude Code, Codex, Cursor and Gemini CLI run inside the same environment, and any agent that speaks MCP can drive a factory.

A shared layer called Warp Drive stores workflows, prompts, rules and MCP configuration centrally so every engineer and agent works from the same conventions. A published Agent Kits gallery offers prebuilt agent packages across engineering, growth, sales, recruiting, research and trust and safety, each with its own trigger, skill file, model and integrations.

For teams, Warp holds a SOC 2 Type 2 attestation with a trust center and offers SAML SSO, enforced single sign on and domain verification. Zero data retention applies with contracted model providers. An autonomy dial runs from approving every step to full autonomy, each agent gets a non human identity with fine grained permissions, and audit trails reach the level of individual tool calls. Enterprises can self host cloud agents and factory workers on their own infrastructure. Warp increasingly builds for managed fleets of agents, not just one agent at a time.

Vendor details

Canonical URL

https://www.warp.dev

Category

Coding agent

Funding status

Independent. Founded by Zach Lloyd, former principal engineer on Google Sheets and the Google Docs suite, and based in New York. Backed by Sequoia Capital, GV, Sam Altman, Marc Benioff and Dylan Field. Reports roughly 800,000 to one million developers, customers including Docker, Ramp, Peloton, Asana, GitHub, NVIDIA, VMware, Amplitude and Teamworks, and over half of the Fortune 500. Core client open-sourced 28 April 2026 under dual MIT and AGPL v3 licensing, with OpenAI as flagship sponsor of the repository; roughly 65k GitHub stars.

Company status

independent

Use cases & customers

Target customers

developersengineering teams

Deployment options

Open-source native client (macOS, Windows, Linux)Warp cloud (SaaS)Self-hosted cloud agents on customer infrastructure (Enterprise)Self-hosted Factories workers in customer VPCDocker- or Kubernetes-backed computeBYOLLM inference through customer's own cloud

Integrations

Agents are summoned from Slack, Linear and GitHub by mentioning @Warp to investigate bugs, suggest fixes or open pull requests, with real time session links and shared visibility. Warp Factories adds Teams, Jira and GitLab, source forge integration, event webhooks with signature verification, a cron scheduler, and MCP server connection management. Warp both ships an MCP server (warp-factory, accepting calls such as send_task) and consumes MCP servers. A REST API at app.warp.dev/api/v1/agent/runs, a TypeScript SDK and a CLI drive agent runs programmatically. Published Agent Kits demonstrate tool calling across HubSpot, Stripe, Intercom, Metabase, BigQuery, Notion, Mintlify, Sentry, Apollo, Grain, Exa and Octolens.

In practice

Your day is DevOps and debugging in a shell, not feature work in an editor. Warp Agent, Warp's built in coding agent, works through tasks of several steps right in the terminal, chaining commands, reading the output, and deciding what to do next as it goes.

A long terminal session has buried the one stack trace you need. Warp groups every command into a block with its output and exit code, so you select, filter, or share just that result instead of scrolling.

You want a flaky test fixed without anyone at the keyboard. A Warp Cloud Agent triggers on the CI failure, pulls the stack trace, proposes a fix, and opens a pull request, recording every step for audit.

Agentic Index coverage score

13.0 / 14 capabilities · 93%

Integrations & Tool Calling Full

Warp connects to Slack, Linear and GitHub so an agent can be summoned by mentioning @Warp inside those tools to investigate bugs, suggest fixes or open pull requests, and Factories adds Teams, Jira, GitLab and source forge integration plus MCP server connection management; the published Agent Kits show tool calling across CRM, billing, support, analytics, documentation, monitoring and search classes including HubSpot, Stripe, Intercom, Metabase, BigQuery, Notion, Mintlify, Sentry, Apollo, Grain, Exa and Octolens, and agents run arbitrary CLI tooling inside their sandbox.

Sourcewarp.dev/pricing integrations section, warp.dev/factories and warp.dev/agent-kitsread 2026-08-30

Workflow Orchestration Full

Multi-agent orchestration on the generally available Automation Platform lets a parent agent spawn and coordinate child agents across local and cloud runs, for supervisor and worker, fan-out, critic, DAG and swarm workflows, started from the Warp app, the Oz CLI, the Oz web app or the Oz API and SDK, with parent and child conversations and artifacts inspectable; local and cloud agents hand work off to each other. Warp Factories, in early access, adds a six stage factory line defined in factory.yaml.

Sourcedocs.warp.dev platform orchestrationread 2026-09-29

Knowledge Grounding & RAG Full

Codebase Context semantically indexes a repository's Git-tracked files so agents can retrieve relevant code, and it applies the same way in the app, the CLI and cloud runs; paid plans carry the highest indexing limits and Enterprise adds custom codebase indexing. Warp Drive stores team workflows, prompts and rules, and MCP servers connect external sources per agent.

Sourcedocs.warp.dev agents capabilities (Codebase Context) and warp.dev/pricingread 2026-09-29

Human Oversight & Guardrails Full

Customers control exactly how much autonomy agents have, from approving every step to allowing full autonomy, set at individual and enterprise level. In Factories the line stops wherever the customer decides, with named gates for spec approval, code review and QA, and merge always stays with the customer. The platform enforces approval gates before merge, pauses and resumes from checkpoints, and offers fine grained permissions per agent, network egress policy enforcement and centrally managed permissions with centrally configured agent access.

Sourcewarp.dev/pricing privacy section, warp.dev/factories and warp.dev/enterpriseread 2026-08-30

Security, Identity & Governance Full

Warp holds a SOC 2 Type 2 attestation from an accredited third party, with the report available on request through a Trust Center. SAML based SSO comes on Business, and Enterprise adds enforced single sign on through a provider such as Okta plus domain verification.

Data is encrypted with AES 256 or higher at rest and TLS 1.3 in transit, Zero Data Retention with all contracted LLM providers means no customer data is retained, stored or used for training, and admins can enforce telemetry, AI and secret redaction controls.

In Factories each agent gets a non human identity with fine grained permissions, secrets storage and rotation, credential handling and network egress policy enforcement.

Sourcewarp.dev/legal/security and warp.dev/pricingread 2026-08-30

Observability & Auditability Full

Every generally available cloud agent run keeps a persistent record with status, metadata, cost and a session transcript covering the prompt, plan, commands, logs, files changed, outputs and follow-up messages; the Runs page in the Oz web app finds runs by source, status, trigger or owner, opens the transcript and shares it for review, and the control plane records run history. Enterprise adds an Analytics API and the client offers a Network Log.

Sourcedocs.warp.dev platform (Viewing cloud agent runs, Platform architecture) and warp.dev/pricingread 2026-09-29

Memory & State Persistence Partial

Agent Memory is a persistent store on Warp that agents read from and write to across harnesses (Warp Agent, Claude Code, Codex), attachable to agents read-only or read-write, so facts, decisions and outcomes carry from one conversation to the next. What ships today is cloud conversation storage, Warp Drive objects and run continuity. Agent Memory is in research preview, enabled per team for design partners through a waitlist.

Sourcedocs.warp.dev agents (Agent Memory, research preview) and warp.dev/pricingread 2026-09-29

Deployment & Data Residency Full

Enterprise plans offer self hosted cloud agents on the customer's own infrastructure and inference routed through the customer's own cloud. Factories runs on Warp's cloud or fully self hosted inside the customer's own VPC under their existing retention and compliance rules, with self hosted workers and the customer's own code forge for factory config.

Compute is backed by Docker or Kubernetes with a sandbox provisioned for each run, and the client itself is a native application for macOS, Windows and Linux whose source is public under MIT and AGPL. The hosted SaaS path stores Warp Drive and account data on Google Cloud Platform with database locations in the United States and no region selection offered.

Sourcewarp.dev/pricing, warp.dev/factories and warp.dev/legal/securityread 2026-08-30

Prebuilt Agents, Templates & Packs Full

Agent Kits is a published gallery of pre built agent packages described as one click to deploy with full control to customize, cataloged across Growth, Sales, Recruiting, Research, Risk Trust and Safety, and Engineering, each shipping a named trigger, a skill file, a default model and its integrations, including Conversion Ratio Optimization, Churn Intervention, Documentation, Social Monitoring, Go to Market, Account Status, POC, Recruiting Sourcing, Competitive Intelligence, Fraud Detection and Client Release agents; Warp Drive additionally stores reusable workflows, prompts and rules as unlimited objects on paid plans, and factory.yaml defines reusable agent types such as FOREMAN and REVIEW as code.

Sourcewarp.dev/agent-kits and warp.dev/factoriesread 2026-08-30

Triggers & Channel Coverage Full

On the generally available Automation Platform, cloud agents start without anyone typing a prompt. Scheduled Agents run on a cron schedule (oz schedule create), GitHub Actions and other CI events start runs, Slack, Linear and Jira integrations pick up work, and the Oz API starts runs programmatically. The terminal, CLI, web app and IDE surfaces cover invoked runs. Warp Factories, in early access, adds further webhooks.

Sourcedocs.warp.dev platform triggers (Triggers overview, Scheduled Agents, GitHub Actions)read 2026-09-29

Model Flexibility & Routing Full

A model picker spans Anthropic, OpenAI, Google and open models with an Auto option, and the customer can run different tasks on different models in parallel or switch model mid task. Bring your own API keys and custom inference endpoints work on every plan, though companies over ten employees need Business or Enterprise for them. Enterprise routes inference through the customer's own cloud as BYOLLM. In Factories, each factory sets a default model and factory.yaml can override it per agent.

Sourcedocs.warp.dev pricing FAQs and warp.dev/pricingread 2026-10-25

APIs, SDKs & MCP Extensibility Full

A REST API at app.warp.dev/api/v1/agent/runs accepts a prompt with bearer token authentication and returns a run id and state, a TypeScript SDK exposes client.agent.run, a CLI runs warp agent run-cloud against a named environment, and a warp-factory MCP server accepts tool calls such as send_task against a factory uid; Warp also consumes MCP servers with connection management, ships webhook signature verification, a settings file allowing users and agents to configure Warp programmatically and sync setups across environments, an Enterprise Analytics API, and a client whose source is public on GitHub under MIT and AGPL with docs published as an open repository.

Sourcewarp.dev/factories and docs.warp.devread 2026-08-30

Testing, Debugging & Optimization Partial

Evaluation lives inside Warp Factories, which is in closed early access by application.

There, evals run on the customer's own work with a pass rate tracked over time, benchmarks compare models against each other on the customer's tasks with relative score and cost per run, benchmark regressions are detected, every run is scored in an evals and scoring pipeline, observer agents in self improvement loops open pull requests against the factory config, and insights include cost per pull request and automation rate.

Warp does not describe evaluation, benchmarking or regression tools for the generally available terminal, Agent CLI or cloud agents.

Sourcewarp.dev/factories quality loop sectionread 2026-08-30

Browser & Computer Use Full

Generally available cloud agents can use a computer. In a sandboxed cloud desktop the agent takes screenshots, records annotated video, clicks, drags, types and uses keyboard shortcuts to test UI changes, enabled per run with --computer-use in the Oz CLI, the computer_use_enabled field in the Oz API (default on for Warp's built-in environments) or a toggle in the Oz web app, with screenshots and videos attached to pull requests. The desktop ships with the platform.

Sourcedocs.warp.dev agents capabilities (Computer Use)read 2026-09-29

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·IntegrationsVerified

Warp Factories now works in Microsoft Teams and Azure DevOps Services, available to all Factories customers. Teams users can mention the Warp app in a channel to hand work to an agent, and in Azure DevOps agents can be mentioned from work items and pull requests or triggered by their events, with each factory given its own identity for Git and pull request operations on selected repositories.

Bears on: Workflow orchestration

View source
View all Warp updates →Tracked since Oct 2026 · Verified from public vendor sources

Pricing

Free, then Build at $20 a month ($18 a month billed annually).

Hybrid. A monthly subscription, priced per user on Business, includes a dollar amount of agent usage at API rates, and usage beyond it is pay as you go. Warp Factories has its own plan table, billed on inference, compute and agent usage.

Free tier

Included quota

The Free plan keeps the terminal fully free, with agent usage pay as you go or on the customer's own key. Build ($20) includes $20 of agent usage a month at API rates, Max ($200) includes $200, and Business ($50 per user, up to 25 seats) includes $20 per seat.

What is public

Warp is an agentic terminal built in Rust, with parallel AI agents, now sold alongside Warp Agent CLI and Warp Factories. The terminal itself is free on all platforms, and AI features are the paid layer. The tiers are Free at $0, Build at $20 a month ($18 annual), Max at $200 a month ($180 annual), Business at $50 per user a month ($45 annual, up to 25 seats) and Enterprise at a custom price. All four self serve tier prices are published, and only Enterprise is quoted.

Billing mechanics

A subscription with a monthly dollar allowance of agent usage at API rates on paid plans, then pay as you go. Bring your own key and custom inference endpoints route inference to the customer's own provider on every plan, and companies over ten employees need Business or Enterprise for that.

Cost watchouts

Heavy agent use exhausts the included dollar allowance quickly, after which usage is paid as you go. Warp Factories, in early access, has its own pricing, with pay as you go at 20% above API rates.

Variable cost rationale

Warp meters agent usage in dollars at API rates. Each paid plan includes an allowance ($20 on Build, $200 on Max, $20 per seat on Business), so agentic work is what grows the bill, and usage past it is paid as you go. Warp Factories is billed on its own table, with pay as you go at 20% above API rates. The terminal itself is free, and bringing your own key routes inference to the customer's own provider instead of Warp's allowance.

Additional watchouts

Self serve plans meter agent usage against a dollar allowance at API rates. Warp Factories is in closed Early Access by application, priced on usage per agent run, and select teams receive up to $10,000 in factory usage. Cross harness agent memory is labeled Research Preview on Enterprise.

Overage / add-ons

Beyond the included dollar allowance, agent work is billed pay as you go. Bringing your own key or a custom inference endpoint routes inference to the customer's own provider.

Sales call required

No, self serve available

Free / trial

Free plan at $0 with the full terminal. Agent use on Free is pay as you go or runs on the customer's own model key. No trial is offered on the self serve plans.

Lowest paid plan

Build at $20 a month, or $18 a month billed annually, with $20 of agent usage a month at API rates

Commercial notes

The terminal is free on all platforms, and only AI features are paid. Build ($20) includes $20 of agent usage at API rates and the highest codebase indexing limits. Max ($200) includes $200 of usage. Business ($50 per user, up to 25 seats) adds SAML based SSO, team usage metrics and data controls that admins configure, plus the customer's own API keys with custom inference endpoints. Enterprise adds unlimited seats, BYOLLM inference through the customer's own cloud and self hosted cloud agents on customer infrastructure. It also brings an Enterprise Analytics API, multi admin support and cross harness agent memory (Research Preview).

Key ambiguities

Build replaced the earlier Pro, Turbo and Lightspeed tiers, and Warp now states included usage in dollars at API rates rather than in credits. Enterprise and Factories at scale are priced through sales.

Cancellation / refund

Monthly or annual billing. Refunds within 24 hours on monthly plans or 15 days on annual plans if no credits were used, and add on credits stay valid for 12 months with an active subscription.

Missing data

Enterprise pricing is not published.

Agentic Index verified 2026-10-25

Alternatives to Warp

The closest documented capability profiles to Warp among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Factory13.0 / 14Matches Warp across all 14 documented capabilities
  • Capy12.5 / 14A lighter documented profile than Warp
  • Cognition13.5 / 14Fuller documented coverage on Memory & State Persistence
  • Cursor12.5 / 14A lighter documented profile than Warp
  • GitHub Copilot13.5 / 14Fuller documented coverage on Memory & State Persistence
  • Google Antigravity12.5 / 14A lighter documented profile than Warp

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.