Manus

v1.x

Meta (formerly Butterfly Effect)

Agentautonomousgeneral-purposecloud-agentconsumer
64
Adequate
About This Agent

General-purpose autonomous agent that executes end-to-end tasks in a cloud VM equipped with a browser, shell, and file tools. Launched virally in March 2025 by Butterfly Effect and acquired by Meta in a deal that closed in late December 2025 for over $2B.

Last Evaluated: June 10, 2026
Official Website

Trust Vector Analysis

Dimension Breakdown

🚀Performance & Reliability
+
task completion accuracy

Assessment of end-to-end task completion based on published benchmark claims and independent user testing reports

Evidence
Wikipedia - Manus (AI agent)Strong showing on GAIA-style autonomous task benchmarks at launch; real-world completion varies widely with task ambiguity and website complexity
mediumVerified: 2026-06-10
tool use reliability

Review of integrated tool stack reliability across browsing, shell, and file operations

Evidence
Manus Product PageIntegrated cloud VM toolset: full browser automation, shell, file system, code execution, and document/slide generation
mediumVerified: 2026-06-10
multi step planning

Evaluation of autonomous task decomposition and long-horizon asynchronous execution

Evidence
Wikipedia - Manus (AI agent)Decomposes high-level goals into explicit task plans and executes them asynchronously, continuing after the user disconnects
mediumVerified: 2026-06-10
memory persistence

Review of session workspace persistence and cross-task preference memory

Evidence
Manus Product PageSession workspaces persist files and context; remembers user preferences and prior instructions across tasks
mediumVerified: 2026-06-10
error recovery

Assessment of retry behavior and failure modes from independent reviews

Evidence
Wikipedia - Manus (AI agent)Retries failed steps and adapts plans, but early reviews noted loops, stalls on complex sites, and occasional silent task failures
lowVerified: 2026-06-10
agent collaboration

Review of internal multi-agent architecture versus user-controllable collaboration

Evidence
Manus Product PageInternally orchestrates multiple sub-agent roles (planner, executor, verifier); no user-facing multi-agent composition
lowVerified: 2026-06-10
🛡️Security
+
tool sandboxing

Security architecture review of cloud VM isolation model

Evidence
Manus Product PageAll execution occurs in isolated per-session cloud VMs, never on the user's device
mediumVerified: 2026-06-10
access control

Review of credential handling and account-level controls

Evidence
Manus Product PageConsumer-oriented account model; credentials given to the agent for logged-in browsing are held in the session, with limited enterprise-grade access governance
lowVerified: 2026-06-10
prompt injection defense

Threat surface analysis of autonomous browsing with limited disclosed defenses

Evidence
Wikipedia - Manus (AI agent)Autonomous web browsing across arbitrary sites is a large injection surface; public documentation of mitigations is minimal
lowVerified: 2026-06-10
data isolation

Data architecture review accounting for ownership and jurisdiction transition

Evidence
CNBC - Meta acquires ManusPer-session VM isolation exists, but data residency and processing arrangements are in transition following Meta's acquisition of the Singapore-based, China-originated company
lowVerified: 2026-06-10
open source transparency

Source availability assessment

Evidence
Manus Product PageProprietary agent harness; historically orchestrated third-party models (Claude, Qwen) rather than publishing its own stack
highVerified: 2026-06-10
🔒Privacy & Compliance
+
data retention

Review of published retention practices during ownership transition

Evidence
Manus Privacy PolicySession data, files, and browsing artifacts retained in Manus cloud; retention terms are consumer-grade and being restated under Meta ownership
lowVerified: 2026-06-10
gdpr compliance

Compliance posture assessment during corporate integration

Evidence
CNBC - Meta acquires ManusMeta ownership brings established compliance infrastructure, but policies and processing locations for Manus are still being integrated post-acquisition
lowVerified: 2026-06-10
third party data sharing

Data flow analysis of third-party model routing before and after acquisition

Evidence
Wikipedia - Manus (AI agent)Historically routed tasks to third-party models (Anthropic Claude, Alibaba Qwen); under Meta, model routing and data sharing arrangements are changing
mediumVerified: 2026-06-10
local deployment option

Deployment options assessment

Evidence
Manus Product PageCloud-only consumer service with no self-hosted, on-premises, or offline option
highVerified: 2026-06-10
👁️Trust & Transparency
+
documentation quality

Documentation completeness review

Evidence
Manus Help CenterConsumer-grade guides and use-case galleries; limited technical documentation of architecture, security, or limits
mediumVerified: 2026-06-10
execution traceability

Review of live session visibility and replay features

Evidence
Manus Product Page'Manus's Computer' view shows the agent's browser, shell, and file actions live, and completed sessions are replayable and shareable
highVerified: 2026-06-10
decision explainability

Assessment of plan visibility and progress narration

Evidence
Manus Product PageDisplays its task plan and step-by-step progress narration, though internal model routing decisions are opaque
mediumVerified: 2026-06-10
open source code

Open source assessment

Evidence
Manus Product PageClosed-source product; only minor components and demos have been shared publicly
highVerified: 2026-06-10
community activity

Community engagement analysis of user base and public activity

Evidence
Wikipedia - Manus (AI agent)Viral launch 2025-03-06 with invite waitlist in the millions; open signup May 2025 built a large consumer user base and active social community
mediumVerified: 2026-06-10
⚙️Operational Excellence
+
ease of integration

Onboarding friction assessment for non-technical users

Evidence
Manus Product PageZero-setup web and mobile apps; describe a task in natural language and the cloud VM handles the rest
highVerified: 2026-06-10
scalability

Scalability assessment of concurrent task limits across tiers

Evidence
Manus Product PageMultiple concurrent cloud tasks supported on paid tiers; throughput governed by credit balance and plan limits
mediumVerified: 2026-06-10
cost predictability

Pricing model analysis; variable credit burn per task reduces predictability

Evidence
Manus PricingCredit-based: Free tier with 300 daily credits; paid plans roughly $20-40/mo up to $200/mo. Credit consumption per task varies and is hard to estimate upfront
highVerified: 2026-06-10
monitoring capabilities

Monitoring features assessment

Evidence
Manus Product PagePer-task session views and credit usage tracking; no organizational observability or audit tooling
mediumVerified: 2026-06-10
production readiness

Vendor stability and product maturity assessment during acquisition integration

Evidence
CNBC - Meta acquires ManusMeta acquisition (>$2B, closed ~2025-12-30) secures resources and continuity, but product, policy, and roadmap are mid-integration
mediumVerified: 2026-06-10
Strengths
  • +True general-purpose autonomy: cloud VM with browser, shell, and file tools executes tasks end-to-end
  • +Transparent 'Manus's Computer' live view and replayable sessions show exactly what the agent did
  • +Asynchronous execution continues in the cloud after the user disconnects
  • +Zero-setup web and mobile experience accessible to non-technical users
  • +Meta acquisition (closed ~2025-12-30, >$2B) provides long-term resourcing and infrastructure
  • +Free tier with 300 daily credits allows meaningful evaluation before paying
Limitations
  • !Governance and jurisdiction transition (Singapore/China origins to Meta ownership) leaves data handling policies in flux
  • !Minimal published security documentation; prompt injection defenses for autonomous browsing are unclear
  • !Credit-based pricing with variable per-task burn makes costs hard to predict
  • !Cloud-only with no self-hosted option; sensitive data must enter Manus's VMs
  • !Reliability degrades on complex or ambiguous tasks, with loops and silent failures reported
  • !Closed-source stack with opaque routing to underlying models (historically Claude and Qwen)
Metadata
license: Proprietary
supported models
0: Anthropic Claude (historical backend)
1: Alibaba Qwen (historical backend)
2: Meta model integration in progress post-acquisition
programming languages
0: Natural language interface; agent writes Python, JavaScript, and shell internally
deployment type: Cloud (per-session VM with browser, shell, file tools)
tool support
0: Browser automation
1: Shell and code execution
2: File and document generation
3: Slides and website generation
4: Scheduled tasks
first release: 2025-03-06 (viral invite launch); open signup May 2025
pricing: Free (300 daily credits); paid plans ~$20-40/mo up to $200/mo (credit-based)
company milestones: Built by Butterfly Effect (Singapore HQ, Chinese origins); acquired by Meta for >$2B, deal closed ~2025-12-30

Use Case Ratings

research assistant

Flagship use case: autonomous multi-source web research, comparison shopping, screening, and report generation

data analysis

Runs code in its VM to clean data, analyze spreadsheets, and produce charts and dashboards from uploaded files

content creation

Generates documents, slide decks, and simple websites end-to-end, though output quality needs human review

code generation

Can build and deploy small apps and scripts, but lacks repository workflows and engineering rigor of dedicated coding agents

education

Builds interactive course materials and explainers; replayable sessions show how tasks are accomplished