Back to home

Platform overview

How Agentique works

Agentique is a free sharing hub for AI-agent resources. It helps users discover, inspect, upload, review, download, and discuss reusable resource profiles, external services, skills, workflow templates, downloadable packages, bundles, and examples while keeping review status and product boundaries visible.

The user path is inspectable end to end.

Each step is designed around reuse decisions: what the resource is, who published it, what it can touch, what review notes are available, which handoff is available, and what the user should confirm before adoption.

Prepare with Creator Kit

Creators can review starter templates, local checks, workflow guidance, upload preparation notes, and status helper documentation before website upload; package promotion and marketplace-style distribution remain separate.

Browse and search

Start from the public catalog, then compare task fit, resource type, review status, compatibility, source and package notes, freshness, warnings, and community feedback.

Inspect before reuse

Resource pages show descriptions, source and package references, file checks, compatibility notes, publisher context, and review status before download or external handoff.

Upload with checks

Publishers choose the clearest resource type and submit descriptions, source links, service or package details, capability notes, and examples through a guided wizard instead of a raw file drop.

Scan and review

Uploads are treated as untrusted input. File checks, risky-content checks, warning states, and review gates run before public reuse.

Download with context

Download handoff keeps source references, version, checksum context, review notes, and non-execution disclosure attached so adoption is deliberate.

Interact and improve

Users can react, review, comment, collect, share, and follow updates so resource quality improves through visible community feedback.

Supported agent formats.

Agentique can register, inspect, review, and display context for multiple agent shapes. Normal intake stays no-execution, and third-party hosted running is not part of the current public path.

Resource profiles

Profiles describe what a resource does, what it needs, what it can connect to, and where users can find source or support information.

External services

External service listings show ownership and freshness notes. The service stays with its provider, and Agentique does not run user tasks through it.

Downloadable resources

Downloadable resources can show file lists, checks, source references, and review notes. Agentique does not install or run submitted package contents.

Tool-aware packages

Commands, setup steps, outside connections, and bundled tools are shown for review instead of being hidden or run automatically.

Skills and workflows

Skills, workflow templates, examples, and bundles stay first-class resources with compatibility notes, setup context, and community feedback.

Future hosted resources

Resources meant for a future hosted path can be described for review, but Agentique does not run third-party resources as hosted workloads in the current public product.

Resource types stay explicit.

Agentique treats agent resources as structured records rather than anonymous files, so users can compare capabilities, compatibility, source, handoff, and review status before reuse.

Scanning and review are platform responsibilities.

Agentique acts as a review layer for shared resources. The upload path assumes submissions may be risky or misleading, then records readable notes for users and reviewers.

Fail closed before public reuse

Suspicious packages can be quarantined for review. High-risk capabilities, unclear source claims, unsafe scripts, and workflow changes are surfaced as review notes instead of hidden behind a generic trust badge.

  • No-execution intake for untrusted uploads
  • Static checks for risky scripts, setup steps, outside connections, unsafe files, and dependency signals
  • External service registration with ownership checks and bounded public information
  • Prompt-risk, tool-risk, credential-risk, and permission-risk notes
  • File checks, source references, and package evidence kept with the resource
  • Private or organization-scoped records filtered before public display
  • Hold and human-review checkpoints for suspicious submissions
  • Clear consent language for high-risk actions and external handoffs

Trust is built from multiple signals.

A resource can be useful and still risky. Agentique separates identity, package, workflow, review, and community signals so users can make a narrower decision.

Publisher identity

Creator pages, verification lifecycle, namespace claims, and social/source signals make provenance easier to compare.

Package and service clarity

Compatibility, service freshness, file checks, package references, and bundle membership stay visible instead of being collapsed into a single download button.

Workflow clarity

Workflow resources show cleaned steps, capability boundaries, and reviewable changes before users adopt or adapt them.

Review status

Scan state, review state, moderation signals, and unsafe-artifact warnings are part of the resource record.

Boundaries are part of the product.

Clear limits keep the shared catalog useful without pretending that every deployment, integration, or runtime concern is already open to the public.

Free sharing catalog

Agentique is positioned as a free community sharing platform. Paid marketplace, escrow, bidding, and revenue-share mechanics are not part of the current product path.

Not hosted execution by default

Resources are inspected, described, downloaded, and discussed. Running third-party agents as hosted workloads remains gated behind explicit future safety and deployment controls.

Advanced integrations stay gated

Public browsing is separate from automation-oriented integrations. External automation routes remain feature-gated until production readiness is proven.

User consent before risky handoff

Capability notes, download context, setup guidance, and high-risk warnings are designed so agents and users can pause before adopting external resources.

Built for shared learning, not one-off downloads.

Profiles, personal libraries, notifications, collections, reviews, reactions, issue context, and creator pages keep resource adoption connected to ongoing community feedback.

Create an account