# Manus — General-purpose AI agent that plans and executes multi-step tasks on its own cloud computer. > Source: The Agents Index — https://theagentsindex.com/manus (structured, researched, re-verified) > Facts last verified: 2026-09-19 Manus is a hosted general-purpose AI agent that plans and executes multi-step tasks in its own cloud computer, producing research, slides, data analysis and deployed full-stack web apps. A REST API, MCP connectors, desktop and Slack surfaces drive the same agent. | Fact | Value | | --- | --- | | Website | https://manus.im | | Price | from $20/month billed monthly, $17/month billed annually | | Free tier | Yes | Free plan is $0/month with 300 daily refresh credits, capped at 1,500 credits of daily refresh per month, 1 concurrent task and 2 scheduled tasks, and Agent Mode limited to Manus 1.6 Lite. Separately, the $40 Pro tier advertises a 7-day free trial. ## What it does **Writes code** · Yes — Generates full-stack applications from a plain-language description, including backend, database and authentication, with no code written by the buyer. > Manus generates the code, sets up the database, configures authentication, and designs your interface—automatically. > — https://manus.im/features/webapp · 'Go from idea to live website in three steps', step 2 Build **Debugs and fixes** · Yes — Runs what it builds in its own browser, finds the failure and fixes it without being asked. > With its integrated browser, Manus can actively test what it builds — launching the application, interacting with it like a real user, detecting issues, and fixing them autonomously > — https://manus.im/blog/manus-1.5-release · Building Complete Web Applications section, closing paragraph **Writes tests** · Partly — Claims it tests the app it just generated; no claim that it authors test code or a test suite. > Generate a full-stack web app with user login, database, and backend, then build, launch, and test it automatically. > — https://manus.im/download · Feature card "Build Web & App without coding" **Whole-codebase work** · Partly — Works across the whole project it builds and keeps a two-way sync with a private GitHub repo, pulling main before each change; carrying a migration across a pre-existing repository is not described anywhere I read. > Automatic Pull: Before making any new code changes, Manus first pulls the latest version from the main branch to reduce the risk of conflicts. > — https://manus.im/docs/website-builder/github-integration · 'How to Use It' section, Sync Your Code bullets **Ships it** · Yes — Deploys what it builds on managed infrastructure with a custom domain, so it goes past the diff; the API exposes the same publish step and deploys require a confirmation. > With Manus, deploying your application is as simple as giving a command. There are no servers to provision, no deployment scripts to write, and no separate hosting accounts to manage. > — https://manus.im/docs/website-builder/cloud-infrastructure · 'Deployment: Go Live Instantly' section **Done-for-you service** · No — This is self-serve software on published per-month and per-seat plans, not an engagement where the vendor's staff build and run the work for you; only Team buyers get a sales contact. > Manus AI is an autonomous general AI agent designed to complete tasks and deliver results. > — https://manus.im/docs/introduction/welcome · Opening paragraph under 'Welcome' _Not established: Reviews code_ ## How much it does unattended **Runs autonomously** · Yes — Runs a task through to a finished deliverable without step-by-step supervision, and paid plans allow 20 concurrent and 20 scheduled tasks running unattended. > This means Manus AI can work independently, remember context across long tasks, and deliver production-ready results without you managing every detail. > — https://manus.im/docs/introduction/welcome · 'What Makes Manus AI Different?' section **Multi-agent** · Yes — Wide Research decomposes one request into independent sub-tasks and runs many agents in parallel, each with its own context, then a main agent synthesises the results. > Instead of using a single AI agent that processes items sequentially, Wide Research deploys hundreds of independent agents that work in parallel. > — https://manus.im/docs/features/wide-research · 'What is Wide Research?' section **Agent permissions** · Partly — It pauses for approval on sensitive actions (local commands, deploys, sending Gmail or Outlook mail, calendar writes), but each prompt offers Always Allow or global_allow, which switches that class off for good. > Every command that Manus attempts to execute on your local machine requires your explicit approval. > — https://manus.im/docs/features/desktop · 'Security and Control' section, Explicit Approval paragraph ## Which models it runs on **Claude** · Partly — Claude is selectable only for LLM features inside apps Manus builds for you; you cannot choose it for the Manus agent itself, and Anthropic is not among the disclosed foundational-model subprocessors. > LLM-powered features can run on any of ten models across three providers: OpenAI (GPT-5), Anthropic (Claude), and Google (Gemini). > — https://manus.im/docs/website-builder/ai-capabilities · "Available LLM Models" section, intro paragraph **GPT** · Partly — OpenAI is a disclosed foundational-model subprocessor for Manus itself, and GPT is nameable for LLM features in generated apps, but the agent's model is never user-selectable. > OpenAI United States Foundational models > — https://trust.manus.im/subprocessors · Subprocessors table, OpenAI row (name / location / purpose cells) **Open models** · No — The disclosed subprocessor list names only Google Cloud Platform and OpenAI as foundational-model providers; no open-weight model is named anywhere as running Manus. > Google Cloud Platform United States Cloud infrastructure and foundational models > — https://trust.manus.im/subprocessors · Subprocessors table (9 rows, closed list) — the only foundational-model rows are Google Cloud Platform and OpenAI **Model choice** · Partly — The platform is deliberately model-agnostic but the vendor does the choosing; users only pick between Manus's own tiers, and the Lite tier is all a free account gets. > Being LLM-agnostic, Manus selects the right model for each use case so users don't have to. > — https://trust.manus.im/ · FAQ, 'What foundational models does Manus use?' expanded answer ## Where you use it **In your editor** · Partly — There is a VS Code instance inside Manus's own cloud computer that you can take over mid-task, and GitHub sync lets you work in your own editor, but the pages read document no plug-in for your IDE. > the user can take control of Manus's computer, operating the browser or VS Code to help Manus overcome certain challenges in the tasks > — https://help.manus.im/en/articles/11711218-how-can-i-take-over-manus-browser-or-vs-code · Opening paragraph of the article **On the command line** · Partly — Through the desktop app the agent drives your machine's command line and the API exposes terminalExecute confirmations, but no Manus CLI client you type commands into is documented. > Manus can use any tool that is accessible from your computer's command line (CLI). > — https://manus.im/docs/features/desktop · FAQ, 'What kind of tools can Manus use on my computer?' **In your pipeline** · Partly — The GitHub connector lets it open and close pull requests and issues and keeps main in two-way sync, but no CI runner, GitHub Action or pipeline trigger is documented on the pages read. > Work with Pull Requests: Create, view, edit, and close pull requests. > — https://manus.im/docs/website-builder/github-integration · 'GitHub Connector Capabilities' bullet list **In a browser** · Yes — The hosted web app is the primary surface and the place connectors are authorised; the same account also has macOS and Windows desktop apps and a mobile app. > Before using a connector via the API, authorize it in the Manus web app > — https://open.manus.ai/docs/v2/connectors · 'Setup' section, first sentence ## Whose machine it runs on **Self-hosted** · No — The agent runs on Manus-operated cloud machines (the Trust Center lists Google Cloud, AWS and Azure as its infrastructure), and no published plan offers a customer-hosted deployment; only the desktop app touches your own hardware. > It operates in a complete sandbox environment—a virtual computer with internet access, a persistent file system, and the ability to install software and create custom tools. > — https://manus.im/docs/introduction/welcome · 'What Makes Manus AI Different?' section _Not established: Open source_ ## What it costs to run **How it meters** · Yes — Billing is per credit, burned by LLM tokens, cloud VM time and third-party API calls, on top of a per-month plan or a per-seat Team price; hosting a built site is metered separately. > The specific credits consumption for a task is determined by its complexity and duration. > — https://help.manus.im/en/articles/11711097-what-are-the-rules-for-credits-consumption-and-how-can-i-obtain-them · 'How do credits work?' section **Free tier** · Yes — A standing $0 plan exists with 300 daily refresh credits, one concurrent task and two scheduled tasks, limited to the Lite model; it is not shown on the pricing page itself. > Free Plan Price: $0/month > — https://help.manus.im/en/articles/11711111-what-is-the-current-membership-pricing-for-manus · Heading of the Free plan section **API access** · Yes — A documented REST API with API keys or OAuth2 creates and polls tasks, uploads files, manages projects, skills, agents and webhooks; per-user rate limits apply and v1 is deprecated. > The Manus API allows you to programmatically create and manage AI agent tasks. > — https://open.manus.ai/docs/v2/introduction · 'Manus API' introduction paragraph **MCP server** · Partly — Manus is an MCP client (prebuilt MCP connectors on every plan plus your own custom MCP servers), but no Manus-hosted MCP server another agent could query is documented; the REST API is the way in. > Manus includes several prebuilt MCP servers on all plans. > — https://manus.im/docs/integrations/mcp-connectors · 'What are MCP Connectors?' section, closing paragraph **Bring your own key** · Partly — You supply your own third-party keys for connectors and for apps Manus builds, and it stores them server-side, but there is no documented way to point the agent's own inference at your keys or cloud. > Manus will store the API key as an environment variable on the server and will not expose it in the client-side code. > — https://manus.im/docs/website-builder/third-party-integrations · 'Adding API Secret key' section ## Buying it for a team **A company can buy it** · Yes — A Team plan sells to an organisation with unified billing that tracks headcount, seats can be added or removed at any time, and enterprise buyers get a sales contact. > You can invite members to your team anytime. Your bill adjusts at the next billing cycle to match your team size. > — https://manus.im/team · Frequently asked questions, 'How does the flexible billing work?' **Seat model** · Yes — Team is priced per seat (US$20 a month or US$200 per seat a year), with each seat adding 4,000 credits to the pool; no seat floor or ceiling is published on the pages read. > Team Plan Price: Starting from $20 per seat/month (Enjoy a 17% discount with annual billing) > — https://help.manus.im/en/articles/11711111-what-is-the-current-membership-pricing-for-manus · Heading of the Team plan section **Pooled budget** · Yes — Team seats share one credit balance rather than each holding its own, so heavy users draw on what lighter colleagues leave unspent before add-on credits are needed. > Each billed user adds credits to your team's shared pool. This eliminates waste and maximizes your subscription value. > — https://manus.im/team · Frequently asked questions, 'How do pooled credits benefit my team?' **Admin controls** · Partly — Team owners and super admins get an admin dashboard with access control and, once SSO is on, a security policy choosing how members may join; no published control constrains what the agent itself may do. > Admin dashboard with usage tracking and access control > — https://manus.im/team · 'Simple, transparent pricing' Team card, feature bullet list **Audit log** · Partly — Audit logs are listed as a Team plan feature alongside the compliance claims; nothing on the pages read says individual and Pro accounts get them, or what events are recorded. > Audit logs and enterprise-grade compliance (SOC 2 Type II, ISO 27001) > — https://manus.im/team · 'Simple, transparent pricing' Team card, last feature bullet **Single sign-on** · Partly — SSO is a Team-plan subscription that only owners and super admins can enable, with a verified domain and the identity provider configured through WorkOS; the pages read never name SAML or OIDC. > click on the “Manage in WorkOS” button to configure your SSO with your chosen third-party Identity Provider > — https://help.manus.im/en/articles/12807937-where-can-i-enable-subscribe-to-a-single-sign-on-sso-subscription-for-manus-team · 'Where can I enable the SSO subscription?', Step 6 ## What happens to your code **Opt out of training** · Partly — The Trust Center states contracts bar every third-party model provider from training on your data, but the Team FAQ frames that prohibition around Team and Enterprise customers and the help centre lists Data Training Opt-Out as a Team feature. > We maintain formal agreements with all third-party model providers to ensure they do not use your data for training their models. > — https://trust.manus.im/ · FAQ, 'What foundational models does Manus use?' expanded answer **Data residency** · Partly — Storage locations are disclosed as the US and Singapore with SCCs covering transfers, and the company is headquartered in Singapore, but no page read offers a customer-selectable region. > For international transfers, we use EU Standard Contractual Clauses (SCCs) and other appropriate safeguards to ensure adequate protection. > — https://trust.manus.im/ · FAQ, 'Where is the data stored?' expanded answer **Getting out** · Partly — Code for anything it builds can be downloaded whole or exported to your own GitHub repo, but credits are the opposite: unused plan credits are wiped each cycle and reset to zero when a subscription ends. > Manus does not allow unused credits to roll over to the next cycle. At the start of each new cycle, all unused credits are cleared and replaced with the new allocation for that cycle. > — https://help.manus.im/en/articles/11711097-what-are-the-rules-for-credits-consumption-and-how-can-i-obtain-them · 'Policy on Unused Credits and Rollover' section **Certifications** · Yes — The Trust Center publishes SOC 2 Type I and Type II attestations plus ISO 27001 and ISO 27701 certificates for download, and the privacy policy addresses EU and UK GDPR roles. > We are SOC 2 compliant. We do not train models on your data. > — https://manus.im/team · 'A secure, collaborative Action Engine' section, Enterprise-Level security card ## 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 | | --- | --- | --- | | caixinglobal.com | Independent source | 2026-08-23 | | cnbc.com | Independent source | 2026-08-23 | | techcrunch.com | Independent source | 2026-08-23 | | riotimesonline.com | Independent source | 2026-08-23 | ## What changed - 2026-09-19 — Capabilities · Commercial terms · Free tier - 2026-09-02 — Capabilities · Commercial terms · Free tier - 2026-08-31 — Capabilities · Commercial terms · Free tier · Price - 2026-08-23 — Alternatives · Summary - 2026-08-19 — Summary ## Correcting this record Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Manus, 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.