# Factory Development platform with Droids, agents that work on software tasks in the terminal, apps, Slack, Jira and CI. Canonical profile: https://ki-agentenkompass.de/en/agents/factory/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-11-05 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Factory is the provider and the platform, Droid is the agent and the command-line app. The domain factory.ai redirects to factory.com. - Provider: Factory AI - Product family: Factory - Profile type: Platform with coding agents (Droids) - Environment: Droid CLI for macOS, Linux and Windows, desktop, web and mobile apps, Slack, Microsoft Teams, Jira, Linear and CI - Connections: Slack, Microsoft Teams, Jira, Linear, GitHub, MCP, skills, subagents, hooks and custom models - Setup: Install Droid or download the desktop app and sign in through the browser. For automations you set up triggers and instructions in the Factory app. - Pricing model: Paid: Pro from 20 US dollars a month, plus Teams, Business and Enterprise per the pricing page. No free plan is listed there. ## Key features ### Droid in many places According to the website, Droid runs in the terminal (interactive or headless), in desktop, web and mobile apps, in Slack and Teams, with Jira and Linear, and in CI pipelines. Source: https://factory.com/ ### Automations Droid starts on a schedule, on Slack messages, GitHub events or webhooks. Guided setups exist, such as triage and code review. Source: https://docs.factory.com/automations/overview ### Missions for larger projects You plan with Droid and approve the plan; an orchestration layer then runs the execution. You can pause it and intervene. Source: https://docs.factory.com/missions/overview ### Droid Computers and Remote Control Droid Computers are persistent environments hosted by Factory. With Remote Control, Droid works on a computer you manage yourself. Source: https://docs.factory.com/droid-computers/overview ### Autonomy levels and command rules The autonomy levels are off, low, medium and high; the default is off with manual approval. Commands can be allowed, asked about or blocked by rule. Source: https://docs.factory.com/droid-cli/settings ### Models and your own keys The documentation names models from Anthropic, OpenAI, Google, xAI and open models. You set up your own endpoints and keys through Custom Models (BYOK). Source: https://docs.factory.com/models ### Customisable harness AGENTS.md, connectors, MCP, subagents, skills, custom slash commands, plugins and hooks extend Droid. Source: https://docs.factory.com/ ### Enterprise controls and EU deployment Admins control models, MCP, retention and sync. For Factory Managed there is a separate EU deployment for enterprise customers. Source: https://docs.factory.com/enterprise/network-and-deployment ## Example workflows ### Recurring code reviews - Your input: A GitHub repository and an automation using the code review setup. - Possible result: Droid runs on repository events such as pull requests and returns feedback. - What to check: Spot-check the feedback and keep the automation’s permissions small. ### Feature with plan and approval - Your input: A project with AGENTS.md and a clearly described feature. - Possible result: Droid drafts a plan, carries it out after your approval and tests the change. - What to check: Read the plan before approving, check the diff and tests, keep autonomy low. ## Requirements and limits ### Paid plan needed Requirement: The pricing page lists no free plan; the lowest plan is Pro at 20 US dollars a month. Source: https://factory.com/pricing ### Missions need testable projects Requirement: For Missions, the documentation expects the best results with a repository at Agent Readiness level 4 or above and, in existing projects, a scriptable way to test the app like a user. Source: https://docs.factory.com/missions/overview ### Command rules are not a sandbox Limitation: According to the documentation, command rules do not cover every program behaviour. It recommends pairing them with sandboxing, managed hooks and least-privilege credentials. Source: https://docs.factory.com/enterprise/llm-safety-and-agent-controls ### EU deployment only through sales Limitation: The EU deployment is an enterprise feature within Factory Managed, for customers with European data residency requirements; the organisation is provisioned through sales. Source: https://docs.factory.com/enterprise/network-and-deployment ### Plan coverage of automations and Remote Control Not yet confirmed: The automations and Remote Control pages do not say which plans include them. Source: https://docs.factory.com/automations/overview ### Training on customer data Not yet confirmed: The data flows page does not say whether customer data is used for model training. Source: https://docs.factory.com/enterprise/privacy-and-data-flows ## A good fit if … - you want to trigger coding tasks from the terminal, Slack or CI and repeat them through automations - you want to plan larger projects, approve them and have an orchestration layer carry them out - you need admin controls such as model policies or an EU deployment for your company ## Less suitable if … - you are looking for a free plan - you need EU data residency without an enterprise contract - you want to inspect and self-host the agent’s source code Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice You choose from Anthropic, OpenAI, Google and xAI models plus open models, or let the Factory Router decide. In the CLI and desktop app you can also add your own models with your own key and any base URL, including OpenRouter, Ollama and LM Studio. According to Factory, only the official Anthropic and OpenAI APIs are fully tested, and organizations can restrict custom models. - Model families named: Anthropic (Claude), OpenAI (GPT), Google (Gemini), xAI (Grok), Mistral, Z.ai (GLM), Moonshot (Kimi), Alibaba (Qwen), DeepSeek, MiniMax, Nvidia (Nemotron) · Other models can be connected freely - Model choice: Automatic or your choice - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes - Depends on: Admin approval Documented · Sources accessed on: 2026-11-05 - [Factory: Models](https://docs.factory.com/models) - [Factory: Custom Models (BYOK)](https://docs.factory.com/cli/byok/overview) ## Europe & regional availability Deployment, data flow and enterprise pages and the pricing page reviewed. The trust centre returned no usable content. Reviewed scope: Platform with cloud services; code runs on your machine or in Factory environments Reviewed on: 2026-11-05 ### EU deployment for enterprise customers With requirements Factory Managed has a separate EU deployment that, per the page, is available to enterprise customers with European data residency requirements. Session content is stored there in a European database and model requests go only to EU-region endpoints. Organisation records, user profiles and billing stay in the global (US) deployment. Sales provisions the EU organisation. Region covered: EU/EEA Documented reason: Only for enterprise customers with data residency requirements and through sales. Official source: https://docs.factory.com/enterprise/network-and-deployment Official source: https://factory.com/pricing Official source: https://docs.factory.com/enterprise ### United Kingdom and Switzerland: no statement Availability still unclear The reviewed pages name no availability or data region for the United Kingdom or Switzerland. Region covered: United Kingdom and Switzerland Documented reason: No country statement in the reviewed sources. Official source: https://docs.factory.com/enterprise/network-and-deployment Official source: https://factory.com/pricing ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Factory account, sign-in through the browser Sources reviewed: 2026-11-05 ### Account used Documented: Droid signs you in through the browser if prompted; the web app is at app.factory.ai. Business and Enterprise list SSO, SAML and SCIM; identity is global per the page (WorkOS-based SSO). Evidence: https://docs.factory.com/droid-cli/quickstart Evidence: https://docs.factory.com/ Evidence: https://factory.com/pricing Evidence: https://docs.factory.com/enterprise/network-and-deployment ### Admin approval Documented with conditions: Org admins can control models, MCP allowlists, session sync and retention through managed settings. The pricing page lists basic admin controls for Business and full admin controls for Enterprise. Enforcement of the MCP allowlist is off by default. Evidence: https://docs.factory.com/enterprise/hierarchical-settings-and-org-control Evidence: https://factory.com/pricing ### Data access & team sharing Documented: Droid works on your machine with command rules (allow, ask, block). Autonomy starts at off with manual approval. The sandbox setting can isolate commands and file access and limit network domains. Evidence: https://docs.factory.com/enterprise/llm-safety-and-agent-controls Evidence: https://docs.factory.com/droid-cli/settings ## Prices and included usage Pricing checked: 2026-11-05 The pricing page lists Pro (20 US dollars), Plus (100), Max (200), Teams (60 per team plus 40 per seat), and Business and Enterprise on request. It lists no free plan. ### Pro 20 US dollars per month Desktop, CLI and SDK, cloud and local background agents, usage stats, agent readiness dashboard; individual use. Price source: https://factory.com/pricing ### Plus 100 US dollars per month Everything in Pro plus Droid Computers; about 5x Pro usage. Price source: https://factory.com/pricing ### Max 200 US dollars per month Everything in Plus plus early access to new features; about 10x Pro usage. Price source: https://factory.com/pricing ### Teams 60 US dollars per team plus 40 per seat per month Everything in Pro for the team, centralised billing, up to 10 seats. Price source: https://factory.com/pricing ### Business On request Custom usage limits, SSO, SAML/SCIM, zero data retention, audit logging, admin controls. Price source: https://factory.com/pricing ### Enterprise On request Everything in Business plus on-premise options, sub-organisations, data residency and premium support with SLAs. Price source: https://factory.com/pricing The pricing page names no token amounts, only ratios to Pro. Models count with different multipliers. Pricing details: https://factory.com/pricing ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Terminal, apps and automations Sources reviewed: 2026-11-05 ### Files and working state Documented: Sessions can be resumed with /sessions. Droid Computers keep packages, files and services between sessions and pause automatically when idle. Evidence: https://docs.factory.com/droid-cli/quickstart Evidence: https://docs.factory.com/droid-computers/overview ### Sign-ins Documented: Sign-in runs through the browser. Remote Control requires /login on the computer and network access to the relay for your region. Evidence: https://docs.factory.com/droid-cli/quickstart Evidence: https://docs.factory.com/remote-control ### Starting further runs Documented: Automations start on a schedule, Slack, GitHub or webhook. Missions run an approved plan across several agents. The automations page names no plan coverage. Evidence: https://docs.factory.com/automations/overview Evidence: https://docs.factory.com/missions/overview ### Human intervention Documented: With autonomy off, approval stays manual. Rules of type ask require approval, block rejects with no approval path. Missions are not fire-and-forget per the page: you can pause and intervene. Evidence: https://docs.factory.com/enterprise/llm-safety-and-agent-controls Evidence: https://docs.factory.com/droid-cli/settings Evidence: https://docs.factory.com/missions/overview ### Detecting errors Documented with conditions: In Missions, features have retry limits and a warning appears when one is reached. Risky command attempts can be monitored through OpenTelemetry. The automations page names no error handling. Evidence: https://docs.factory.com/missions/overview Evidence: https://docs.factory.com/enterprise/llm-safety-and-agent-controls ### Resuming after failures Documented: /sessions lists and resumes previous sessions; /fork prints a droid --resume command to open the copy elsewhere. In Missions you can pause the orchestrator and ask it to recover. Evidence: https://docs.factory.com/droid-cli/quickstart Evidence: https://docs.factory.com/missions/overview ### Editorial assessment You get fine control through autonomy levels and rules, but you are responsible for isolation, since rules are not a sandbox. For automations, keep permissions small and check results. ## Memory and conversation continuity Scope: Sessions and AGENTS.md of the Droid agent Sources accessed: 2026-11-05 Sessions can be resumed and AGENTS.md carries project knowledge; the reviewed pages describe no memory of the agent itself. ### Storage and scope Partly documented: The reviewed pages do not say where sessions are stored locally. With cloudSessionSync (default: on), CLI sessions are mirrored to the web app; when off, they stay local. Project knowledge lives in AGENTS.md files. - [Factory: Droid CLI settings](https://docs.factory.com/droid-cli/settings) - [Factory: AGENTS.md guide](https://docs.factory.com/guides/power-user/memory-management) ### Selection and timing Not publicly established: You write and commit AGENTS.md yourself. Whether Droid saves memories itself is not stated on the page. - [Factory: AGENTS.md guide](https://docs.factory.com/guides/power-user/memory-management) ### Inspect, edit and delete Partly documented: /sessions lists and resumes earlier sessions. Org admins set how long cloud sessions are kept with sessionRetentionDays (14 to 365 days). The pages do not describe deleting or editing individual sessions. - [Factory: Droid CLI quickstart](https://docs.factory.com/droid-cli/quickstart) - [Factory: Enterprise controls](https://docs.factory.com/enterprise/hierarchical-settings-and-org-control) ### Agent and channel boundaries Documented: Droid looks for AGENTS.md from the working directory up to the git root and in .factory/, .agents/ and .agent/; personal instructions live under ~/.factory/. Nested files load when reading, editing, listing or searching in their folders. - [Factory: AGENTS.md guide](https://docs.factory.com/guides/power-user/memory-management) ### Retrieval Documented: According to the page, AGENTS.md is loaded into every session, with limits of 80,000 characters at startup and 40,000 per tool call. You bring back earlier sessions with /sessions or droid --resume . - [Factory: AGENTS.md guide](https://docs.factory.com/guides/power-user/memory-management) - [Factory: Droid CLI quickstart](https://docs.factory.com/droid-cli/quickstart) ### Session reset and compaction Partly documented: /fork copies the current session into a new one; the original stays open. The AGENTS.md page says nothing about context compaction. - [Factory: Droid CLI quickstart](https://docs.factory.com/droid-cli/quickstart) - [Factory: AGENTS.md guide](https://docs.factory.com/guides/power-user/memory-management) ## Context A repository, an account on a paid plan and a limited task. According to the documentation command rules are not a sandbox; for more isolation it points to the sandbox setting. Website, pricing page and documentation reviewed. Feature descriptions come from the provider; example tasks are editorial. The trust centre could not be evaluated. Hands-on tests are still pending. ## Open points Europe, availability still unclear: - United Kingdom and Switzerland: no statement Requirements and limits, not yet confirmed: - Plan coverage of automations and Remote Control - Training on customer data ## Sources - https://factory.com/ - https://docs.factory.com/ - https://factory.com/pricing - https://docs.factory.com/droid-cli/quickstart - https://docs.factory.com/enterprise/network-and-deployment - https://docs.factory.com/enterprise/privacy-and-data-flows - https://docs.factory.com/enterprise/llm-safety-and-agent-controls - https://docs.factory.com/models - https://docs.factory.com/droid-cli/settings - https://docs.factory.com/enterprise/hierarchical-settings-and-org-control - https://docs.factory.com/automations/overview - https://docs.factory.com/missions/overview - https://docs.factory.com/droid-computers/overview - https://docs.factory.com/remote-control - https://docs.factory.com/enterprise - https://docs.factory.com/guides/power-user/memory-management - https://github.com/factory-ai/factory ## Provider Factory AI runs the platform and, per the repository README, holds the copyright; the product source is not there, the repository holds documentation and community material. - Operator: Factory AI - Organization: Provider - Website: https://factory.com/ - Reviewed: 2026-11-05 - Provider source: https://factory.com/ - Provider source: https://github.com/factory-ai/factory [Sources and method](https://ki-agentenkompass.de/en/sources/)