Live catalog
This is the browsing surface for products where agent-native behavior, agent-led creation, or agentic workflows are central. For the strategy page, read the AI agent directory. For the review standard, see how MadeWithStack evaluates agent-native products.
82
Approved listings
Products currently visible in this reviewed browse catalog.
0
Claim verified
Listings whose qualification claims have passed separate evidence review.
64
Claim submitted
Listings already in review for the agent claim trust layer.
4
Tracked stack layers
Agent tool categories with live examples attached to approved products.
Trust model
A listing can be approved for publication without automatically receiving a verified qualification claim. That keeps the public catalog useful while preserving a stricter standard for agent-directory provenance.
Approved
The product itself passed editorial review and can appear publicly.
Claim verified
The public qualification claim has supporting evidence strong enough to show as verified.
Browse reviewed products
Every filter and search state lives in the URL so the current directory view can be shared or bookmarked.
Supporting stack signals
Agent Directory listings still keep their frameworks, providers, infrastructure, and platform choices visible. That is how the catalog stays useful for technical evaluation instead of turning into a generic AI feed.
Qualification type
Verification status
Research / Agent-native
Free catalog of 100+ free AI API providers, generation limits (image/video/music), student offers, and alternatives to paid AI tools. Limits rechecked ~72h. EN/ZH/RU.
Search indexed YouTube transcripts for timestamped quotes, speaker appearances, mentions, sponsors and recommendations through an API, MCP server, TypeScript/Python SDKs and CLI.
Convert PDFs into clean, structured Markdown through a web app, REST API, or MCP server. Freemium credits, no subscription.
Agent-native API for repeatable cross-provider AI visibility measurement, citations, competitor share of voice, and workflow triggers.
Free opt-in pizza playtests and discussion boards for agents you already run. Local MCP adapter and signed REST API; messages are readable by authorized participants and the platform operator.
Sports odds API and MCP server for personal and internal research. Use your own API key for private models and line comparison. Free tier: 1,000 credits/month. Public display and redistribution rights are not included.
PuppyOne keeps your project files and AI in one local-first workspace, so your assistants can understand the whole project, work across real files, and continue without starting from scratch.
No-auth IRS Form 990 nonprofit API for AI agents, donor research, charity comparison, governance review, and citations.
Private AI memory and source-backed knowledge platform for teams using agents, helping legal, compliance, research, diligence, and agency teams turn documents and decisions into reusable agent-ready context.
Curated collections
Curated collection
Reviewed products where agent behavior is central to customer support, triage, or service operations.
Stack collection
Products that list Claude in their build stack or agent workflow metadata. Check each listing for supporting sources.
Checked collection
Products whose MCP endpoint passed an automated availability check: an initialize response or an OAuth sign-in requirement. Check authentication requirements and client support before connecting.
Claude
Next.js
Vercel
Cloudflare
Cursor
React
MongoDB
