DEDUPED Hot AI repos, turned into use cases Get 5 a day

FOR AGENTS AND DEVELOPERS

Free API and MCP server

Read-only JSON. No key, no signup, no rate plan. Static files rebuilt daily.

Every use case, hot repo and daily news item on Deduped is also a JSON file. Agents can search the catalog, pull one use case with its steps and agent prompt, and hand it to a coding agent. Fields are only ever added under /api/v1/, never renamed.

Endpoints

GETWhat you get
/api/v1/index.jsonEndpoints and counts
/api/v1/usecases.jsonEvery use case, light record (id, repo, title, summary, category, url)
/api/v1/usecases/<id>.jsonOne use case: steps, agent_prompt, requirements, risks, caveat. id = repo-slug--use-case-slug
/api/v1/search.jsonCompact search index, one small file for client side matching
/api/v1/repos.jsonHot AI repos of the last 90 days, best first
/api/v1/repos/<slug>.jsonOne hot repo with its use cases
/api/v1/news.jsonToday's AI news brief, each story once
/api/openapi.jsonOpenAPI 3.1 spec

Example

curl -s https://dedupedai.com/api/v1/search.json | jq '.items[] | select(.t | test("pdf"; "i")) | .id'
curl -s https://dedupedai.com/api/v1/usecases/<id>.json | jq -r .agent_prompt

MCP server

The deduped-mcp MCP server gives Claude, Cursor and any MCP client four tools: search_use_cases, get_use_case, hot_repos and today_news. It only reads the public JSON above over HTTPS. One Python file, no dependencies.

Claude Code

claude mcp add deduped -- uvx deduped-mcp

Claude Desktop or Cursor (mcp.json)

{
  "mcpServers": {
    "deduped": { "command": "uvx", "args": ["deduped-mcp"] }
  }
}

Not on PyPI yet? Download deduped_mcp.py and use "command": "python3", "args": ["/path/to/deduped_mcp.py"].

Use and attribution

  • Free to read, search and use in your own agent runs and products.
  • When you show a use case to a person, link its url so they see the full steps, caveats and disclaimer.
  • The repos belong to their owners and keep their own licenses. Use cases are AI-generated and can be wrong: read the disclaimer.
  • Agent guide: llms.txt. Questions: [email protected]