Agentic AI Comparison:
Gobii vs project-mariner
vs
(listing unavailable)Introduction
Gobii and Project Mariner are assessed for their documented purposes, access, cost clarity and integrations. Project Mariner’s original service is closed; it is historical context, not a currently adoptable option. Gobii: Gobii’s current MIT source describes durable agents that wake on schedules/events, use browsers, call systems and coordinate through identities/channels. Assess this counterpart’s own current setup and purpose rather than assigning successor Gemini features to Mariner.
Overview
project-mariner
Project Mariner was Google’s experimental browser agent for observing pages and carrying out requested multi-step web tasks. The official 2024 demo is sped up and historical; its published performance is not our listing autonomy score.
Google’s rendered official landing page says Mariner shut down on May 4, 2026 and directs visitors to Gemini Spark for complex tasks. The original service is hidden. That related destination is separate and its capabilities or plans are not attributed to Mariner.
There is no current standalone Mariner offer. Its former Ultra access or historical price cannot be used for a present purchase recommendation.
Former browser/Chrome execution is historical. The original retired service has no active user-facing integration; successor Gemini/API tools are separate products.
Gobii
Gobii’s current MIT source describes durable agents that wake on schedules/events, use browsers, call systems and coordinate through identities/channels. It is an always-running agent platform rather than only a one-shot browser demo.
Source remains accessible and not archived, last pushed August 2026. The cloud/domain fetch failed here; that alone does not establish closure. Self-hosting requires configuration, providers and operations.
Accessible MIT source is separate from inference, hosting and channel costs. Current cloud selected pricing/entitlement was not verified.
The README documents API workflow, remote MCP, browsers, email/text identities and event-driven operation. These source-backed interfaces do not establish every hosted app connector or authenticated delivery.
Editorial ratings · 1–10, higher is better
These scores express our judgement of the cited product facts. They are not measured performance benchmarks. Each product is assessed for its stated purpose; a higher score does not make different workflows interchangeable.
Evidence gaps lower confidence and affect the relevant judgement. Unknown pricing does not mean free access. Research prototypes and retired products retain their historical scope, with adoption ratings reflecting current access.
Ratings assessed: 2026-10-09. Source verification dates may differ.
Documented capability: How useful and complete is the documented workflow for the product's stated purpose?
- 1–2: No usable current workflow established, or only an unsupported promise.
- 3–4: Historical, experimental or very limited workflow; substantial delivery gaps.
- 5–6: Concrete but narrow workflow, or promising research requiring specialist review.
- 7–8: Substantial documented end-to-end workflow with useful controls or customization.
- 9–10: Exceptionally complete documented scope and controls; reserve 10 for unusually strong evidence.
Ease of adoption: Can the intended user obtain and set up a usable product today?
- 1–2: Discontinued, unavailable, waitlisted, or no usable deployment path verified.
- 3–4: Archived software, restricted research/preorder access or uncertain current service access.
- 5–6: Developer-managed setup, significant configuration or sales-led implementation.
- 7–8: Active accessible product with manageable setup for its intended user.
- 9–10: Straightforward self-service access and setup, with unusually few adoption obstacles.
Value and cost clarity: How attractive and understandable is the cost model for the documented use?
- 1–2: No current purchasable or usable offer; historical prices cannot support a purchase.
- 3–4: Material price, entitlement, license or availability uncertainty limits budgeting.
- 5–6: Plausible value with custom pricing, significant setup costs or incomplete selected-plan terms.
- 7–8: Useful scope with clear entry pricing/allowances or accessible source, while accounting for running costs.
- 9–10: Exceptionally accessible and clear cost model for substantial useful scope; never assume free compute.
Integration options: How useful and extensible are the verified user-facing connections for the intended workflow?
- 1–2: No current user-facing connection verified, or former connections are unavailable.
- 3–4: Inputs/exports or one focused connection; internal dependencies are not native connectors.
- 5–6: Useful API, configurable tools or several relevant connections, with limited verified breadth.
- 7–8: Broad relevant connections or an extensible documented API/MCP/tool ecosystem.
- 9–10: Extensive documented ecosystem with multiple connection mechanisms and strong task relevance.
Metrics Comparison
Documented capability
Gobii: 8/10
Evidence confidence: high
Editorial judgement 8/10: Gobii’s current MIT source describes durable agents that wake on schedules/events, use browsers, call systems and coordinate through identities/channels. It is an always-running agent platform rather than only a one-shot browser demo.
project-mariner: 7/10
Evidence confidence: high
Editorial judgement 7/10: Project Mariner was Google’s experimental browser agent for observing pages and carrying out requested multi-step web tasks. The official 2024 demo is sped up and historical; its published performance is not our listing autonomy score.
Project Mariner’s original service is closed; it is historical context, not a currently adoptable option. Gobii: Gobii’s current MIT source describes durable agents that wake on schedules/events, use browsers, call systems and coordinate through identities/channels. Assess this counterpart’s own current setup and purpose rather than assigning successor Gemini features to Mariner.
Ease of adoption
Gobii: 5/10
Evidence confidence: medium
Editorial judgement 5/10: Source remains accessible and not archived, last pushed August 2026. The cloud/domain fetch failed here; that alone does not establish closure. Self-hosting requires configuration, providers and operations.
project-mariner: 1/10
Evidence confidence: high
Editorial judgement 1/10: Google’s rendered official landing page says Mariner shut down on May 4, 2026 and directs visitors to Gemini Spark for complex tasks. The original service is hidden. That related destination is separate and its capabilities or plans are not attributed to Mariner.
Current accessible deployment and human setup are distinct from historical capability.
Value and cost clarity
Gobii: 6/10
Evidence confidence: medium
Editorial judgement 6/10: Accessible MIT source is separate from inference, hosting and channel costs. Current cloud selected pricing/entitlement was not verified.
project-mariner: 1/10
Evidence confidence: high
Editorial judgement 1/10: There is no current standalone Mariner offer. Its former Ultra access or historical price cannot be used for a present purchase recommendation.
Selected entitlement and running costs matter; unknown price is not free access or an arbitrary neutral score.
Integration options
Gobii: 8/10
Evidence confidence: high
Editorial judgement 8/10: The README documents API workflow, remote MCP, browsers, email/text identities and event-driven operation. These source-backed interfaces do not establish every hosted app connector or authenticated delivery.
project-mariner: 1/10
Evidence confidence: high
Editorial judgement 1/10: Former browser/Chrome execution is historical. The original retired service has no active user-facing integration; successor Gemini/API tools are separate products.
Only documented relevant user-facing connections count; roadmap, source-hosting links and successor tools are separate.
Conclusions
Project Mariner’s original service is closed; it is historical context, not a currently adoptable option. Gobii: Gobii’s current MIT source describes durable agents that wake on schedules/events, use browsers, call systems and coordinate through identities/channels. Assess this counterpart’s own current setup and purpose rather than assigning successor Gemini features to Mariner. Ratings are subjective editorial opinions, not measured accuracy, safety, reliability, popularity or scientific benchmarks.
The best framework is the one you can keep current and afford to run.
Run OpenClaw or Hermes with saved memory, one-click runtime updates, and your choice of Platform Credits, provider keys, or supported subscriptions.
Plans start at $199/month. Cancel anytime.
Hosted agent
OpenClaw or Hermes