# Factory — Droid coding agents that run in the desktop app, CLI, IDEs, CI and Factory-managed cloud computers. > Source: The Agents Index — https://theagentsindex.com/factory-ai (structured, researched, re-verified) > Facts last verified: 2026-09-02 Factory is an agent-native software development platform whose Droid agents write, review, test and ship code from a desktop app, terminal, IDE, headless CI runs or hosted cloud computers. Enterprise deployments add org policy, airgapped builds and bring-your-own model endpoints. | Fact | Value | | --- | --- | | Website | https://factory.com | | Price | from $20/month | | Free tier | No | No free plan or trial is published. The six plans are Pro $20/mo, Plus $100/mo, Max $200/mo, Teams $60/mo plus $40/mo per seat, and quote-only Business and Enterprise. Within a paid plan, the Droid Core open-weight pool and a BYOK allowance are free. ## What it does **Writes code** · Yes — Droid authors and patches code from a natural-language task across app, CLI and cloud surfaces. > It uses LLMs to analyze existing code and generate new code, then applies patches on disk, with git as the source of truth where available. > — https://docs.factory.ai/enterprise/privacy-and-data-flows · Code and file access section, bullet list **Debugs and fixes** · Yes — Documented flows include fixing a named bug and repairing failing tests under autonomy levels. > droid exec --auto medium "install deps, run tests, and fix failing checks" > — https://docs.factory.ai/droid-exec/overview · Autonomy Levels section, examples code block **Writes tests** · Yes — The /install-qa skill generates QA sub-skills and executes end-to-end test flows per diff, with evidence. > Execute test flows: Runs relevant flows plus generates targeted tests based on the specific diff. > — https://docs.factory.ai/software-factory/automated-qa · How QA runs, step 4 **Reviews code** · Yes — /review reviews branches, commits or uncommitted diffs locally; a CI workflow reviews pull requests. > The `/review` command provides a local workflow for analyzing code changes with AI-powered insights. > — https://docs.factory.ai/software-factory/code-review · Overview, first paragraph **Whole-codebase work** · Yes — Missions decompose multi-feature work into milestones and are documented for brownfield migrations. > Brownfield migrations: Modernizing existing codebases, swapping frameworks, or restructuring large projects while preserving existing behavior. > — https://docs.factory.ai/missions/overview · What Missions are good for, bullet list **Ships it** · Partly — High autonomy permits pushes, deployments and migrations; the Release stage that tracks ship gates is Private Preview. > --auto high | High-risk automation including remote writes, deployments, database migrations, and commands that may access sensitive data > — https://docs.factory.ai/droid-exec/overview · Autonomy Levels comparison table, --auto high row **Done-for-you service** · No — You run the software; Enterprise adds onboarding and named support staff, not build-and-run delivery. > Dedicated Account Manager and Customer Engineer > — https://factory.com/pricing · Enterprise plan card, Premium support bullets ## How much it does unattended **Runs autonomously** · Yes — Headless droid exec runs one-shot tasks to completion; Missions orchestrate long multi-feature work. > Unlike the interactive CLI, `droid exec` runs as a one-shot command that completes a task and exits, making it ideal for CI/CD pipelines, shell scripts, and batch processing. > — https://docs.factory.ai/droid-exec/overview · Intro paragraph **Multi-agent** · Yes — Task-launched subagents run in fresh contexts, concurrently or in background; Missions orchestrate workers and validators. > To run subagents concurrently, the parent issues multiple Task tool calls in the same turn, or launches several with `run_in_background: true` and collects the results with `TaskOutput`. > — https://docs.factory.ai/harness/subagents · Resuming and parallel runs section **Agent permissions** · Yes — Four autonomy levels (Off/Low/Medium/High) gate tool risk, plus allowlists, denylists and an unbypassable blocklist. > Autonomy Level sets the highest-risk work Droid can run without pausing for approval. > — https://docs.factory.ai/autonomy-and-safety/auto-run · Intro paragraph ## Which models it runs on **Claude** · Yes — Anthropic models are listed natively, from Haiku 4.5 through Opus-class, with per-model usage multipliers. > We support all leading frontier and open-weight models, including the latest versions of GPT-5, Claude Opus and Sonnet, Gemini, and more. > — https://factory.com/pricing · FAQ, "What models do you support?" answer **GPT** · Yes — OpenAI GPT-5 series models are offered natively, including Codex variants, each with a billing multiplier. > We support all leading frontier and open-weight models, including the latest versions of GPT-5, Claude Opus and Sonnet, Gemini, and more. > — https://factory.com/pricing · FAQ, "What models do you support?" answer **Open models** · Yes — Droid Core is an open-weight model pool with its own rate limits, switchable free when standard usage runs out. > When you hit a Standard Usage rate limit, you can switch for free to Droid Core (powered by leading open-weight models) which has a separate rate limit. > — https://factory.com/pricing · FAQ, "What happens if I exceed my limits?" answer **Model choice** · Yes — You pick the model per session, per subagent and per exec run with -m/--model, or add custom endpoints. > -m, --model Model ID to use > — https://docs.factory.ai/droid-exec/overview · Execution model, CLI help excerpt ## Where you use it **In your editor** · Yes — VS Code/Cursor/Windsurf extension shares files and diagnostics; JetBrains and Zed run Droid over ACP. > Droid works in any editor with an integrated terminal. For deeper editor context, use the dedicated integrations for VS Code-family editors, JetBrains IDEs, or Zed. > — https://docs.factory.ai/ide-integrations · Intro paragraph **On the command line** · Yes — The Droid CLI installs via curl, Homebrew, npm or PowerShell and runs in any repository. > Run one command, then start `droid` in any repository. > — https://docs.factory.ai/ · Start with a surface, Droid CLI tab **In your pipeline** · Yes — Droid Exec plus the Factory-AI/droid-action GitHub Action review and act on pull requests inside your runners. > The Factory Droid GitHub Action ([`Factory-AI/droid-action`](https://github.com/Factory-AI/droid-action)) runs **entirely inside GitHub Actions** on runners you control. > — https://docs.factory.ai/enterprise/compliance-audit-and-monitoring · Securing the GitHub Action and CI, first paragraph **In a browser** · Yes — Sessions sync to app.factory.ai in any browser, with nothing to install. > Nothing to install: [cloud session sync](/droid-cli/settings#cloud-session-sync) and [Droid Computers](/droid-computers/overview) make your sessions available from any browser > — https://docs.factory.ai/ · Start with a surface, Web & Mobile tab ## Whose machine it runs on **Self-hosted** · Partly — The agent always runs on your machine, and a dedicated airgap build exists, but airgap builds are Enterprise-only and not publicly distributed. > Airgap builds are an enterprise capability and are not distributed through the public download channels. > — https://docs.factory.ai/enterprise/airgapped-deployment · Info callout under the intro **Open source** · Partly — The CI action is a public repository; the Droid agent itself ships as binaries, with no source offered. > Both platforms run on Droid Action, maintained at `Factory-AI/droid-action`. > — https://docs.factory.ai/software-factory/code-review-ci · Automated Code Review intro, second paragraph ## What it costs to run **How it meters** · Yes — Per-seat subscription with rolling rate limits; model usage draws Standard Credits at per-model multipliers, then prepaid Extra Usage. > Droid sessions consume Factory Standard Credits based on model usage, along with compute usage for Droid Computers. > — https://docs.factory.ai/pricing/individuals · FAQ, "What counts toward each rate limit?" **Free tier** · No — The published plan list starts at Pro $20/mo; no free tier or trial is offered, though Droid Core and a BYOK allowance are free within a paid plan. > Individual plans are for developers who own their own Factory subscription. Pro, Plus, and Max include the Factory App, Droid CLI, and Droid SDK, with usage governed by rolling Rate Limits. > — https://docs.factory.ai/pricing/individuals · Intro paragraph above the plan cards **API access** · Yes — Public REST API at api.factory.ai with bearer keys covers sessions, computers, org, service accounts, CI automations and wiki; TypeScript and Python SDKs exist. > Public API for Factory platform. Requires authentication via the `Authorization: Bearer` header. > — https://docs.factory.ai/api-reference · Page subtitle **MCP server** · Partly — Droid is an MCP client over stdio/http/sse and can be driven by another program over JSON-RPC or ACP, but no Factory-hosted MCP server is documented. > Model Context Protocol (MCP) servers extend Droid's capabilities with extra tools and context. > — https://docs.factory.ai/harness/mcp · Intro paragraph **Bring your own key** · Yes — BYOK covers your own OpenAI/Anthropic keys, OpenAI-compatible gateways, local models and AWS Bedrock; keys stay on your machine. > Yes, you can bring your own keys (BYOK) from your preferred model provider. All Individual plans include an allowance of free BYOK usage. After this allowance, BYOK usage will be charged according to your specific plan. > — https://factory.com/pricing · FAQ, "Can I use my own keys?" answer ## Buying it for a team **A company can buy it** · Yes — Teams is self-serve with centralized billing; Business and Enterprise are contracted plans bought by an organisation. > Business and Enterprise plans are for teams and companies that need shared usage, administrative controls, onboarding, security terms, and support. > — https://docs.factory.ai/pricing/organizations · Intro paragraph **Seat model** · Yes — Teams is $60/mo plus $40/mo per seat, capped at 10 seats; Business is up to 150 seats, Enterprise unlimited. > Teams · $60/mo + $40/seat > — https://docs.factory.ai/pricing/organizations · Plan cards, Teams card title **Pooled budget** · Partly — Teams seats each keep their own Pro rate limits; Business and Enterprise usage is shared across the workspace. > On Business and Enterprise plans, usage is shared across the workspace and governed by contract terms. > — https://docs.factory.ai/pricing/organizations · Usage and billing section **Admin controls** · Partly — Org-managed settings cap autonomy and restrict models, MCP servers, commands and network; listed from Business upward, with full controls on Enterprise. > Basic admin controls (model selection, autonomy level, model access controls, org-level deny lists, network policy) > — https://factory.com/pricing · Business plan card, feature bullets **Audit log** · Partly — Business lists audit logging; the organization audit log view and its API are restricted to Enterprise owners. > The audit log is available to **Enterprise organization owners only**. > — https://docs.factory.ai/enterprise/audit-log · Enterprise Feature info callout **Single sign-on** · Partly — SAML/OIDC SSO with SCIM directory sync via WorkOS, sold from the Business plan; Teams and individual plans have none. > Factory uses **WorkOS** for enterprise identity, supporting domain verification, SSO (SAML/OIDC), and Directory Sync (SCIM). > — https://docs.factory.ai/enterprise/identity-and-access · Domains, SSO, and SCIM section ## What happens to your code **Opt out of training** · Partly — Zero Data Retention is a Business and Enterprise plan feature; Factory says it routes traffic directly to providers and stores no prompts, and never indexes your repository. > In these configurations, Factory routes traffic **directly** to the provider's official APIs; we do not proxy this traffic through third-party services or store prompts and responses in Factory cloud. > — https://docs.factory.ai/enterprise/privacy-and-data-flows · LLM requests and model-specific guarantees, second paragraph **Data residency** · Partly — Data residency and customer-managed encryption keys are Enterprise-only; hybrid and airgapped deployments keep all runtime data in your network. > Customer-managed encryption keys and data residency > — https://docs.factory.ai/pricing/organizations · Plan cards, Enterprise bullets **Getting out** · Partly — Purchased Extra Usage credits never expire and roll over, but monthly Standard Usage does not; no account-wide data export path is documented (AutoWiki has its own export). > No. Standard Usage does not roll over month to month. Extra Usage that you purchase does roll over. > — https://docs.factory.ai/pricing/individuals · FAQ, "Does unused standard usage roll over?" **Certifications** · Yes — SOC 2 Type II, ISO 27001 and ISO 42001, with reports and sub-processor lists in the Trust Center. > Factory maintains an enterprise-grade security and compliance program, including: - **SOC 2 Type II** - **ISO 27001** - **ISO 42001** > — https://docs.factory.ai/enterprise/compliance-audit-and-monitoring · Certifications and Trust Center section ## Provenance Every fact above comes from the vendor. Nothing here is independently corroborated yet. ## Coverage elsewhere Pages about this product that the vendor does not control. The label states how independent each one is. | Source | Kind | Read | | --- | --- | --- | | techcrunch.com | Independent source | 2026-08-23 | | venturebeat.com | Independent source | 2026-08-23 | | cityam.com | Independent source | 2026-08-23 | ## What changed - 2026-09-02 — Capabilities · Commercial terms · Free tier - 2026-08-31 — Capabilities · Commercial terms · Free tier · Price - 2026-08-23 — Alternatives · One-liner · Summary · Website - 2026-08-19 — One-liner ## Correcting this record Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Factory, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth. Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.