https://github.com/unitedideas/nothumansearch
Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.
https://github.com/unitedideas/nothumansearch
agent-discovery agentic-ai ai-agents ai-plugin ai-tools anthropic claude fly-io go llms-txt mcp mcp-server model-context-protocol openapi postgres search-engine
Last synced: 21 days ago
JSON representation
Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.
- Host: GitHub
- URL: https://github.com/unitedideas/nothumansearch
- Owner: unitedideas
- License: mit
- Created: 2026-04-14T00:01:12.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2026-04-24T00:23:00.000Z (28 days ago)
- Last Synced: 2026-04-24T02:26:01.594Z (28 days ago)
- Topics: agent-discovery, agentic-ai, ai-agents, ai-plugin, ai-tools, anthropic, claude, fly-io, go, llms-txt, mcp, mcp-server, model-context-protocol, openapi, postgres, search-engine
- Language: Go
- Homepage: https://nothumansearch.ai
- Size: 626 KB
- Stars: 0
- Watchers: 0
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Security: SECURITY.md
Awesome Lists containing this project
- awesome-a2a - unitedideas/nothumansearch - Not Human Search — agent-first search engine indexing 8,000+ agent-readable services (including A2A-aspiring agents with llms.txt, OpenAPI, ai-plugin, or MCP). Ranked across 7 signals. Exposes MCP server at `https://nothumansearch.ai/mcp` + REST API. Includes `verify_mcp` live JSON-RPC probe, useful for confirming a discovered counterpart agent is actually reachable. (Server Implementations / 🔎 <a name="search-and-data-extraction"></a>Search & Data Extraction)
- awesome-cli-coding-agents - Not Human Search - plugin); 8,000+ indexed sites exposed via MCP server, REST API, and full-text search. Lets agents discover and verify external services before wiring them into a repo. MIT. (Harnesses & orchestration / Agent infrastructure)
- awesome-ChatGPT-repositories - nothumansearch - Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites. (The latest additions 🎉)
README
# Not Human Search
[](https://nothumansearch.ai/site/nothumansearch.ai)
**Search engine for AI agents.** Indexes sites ranked by *agentic readiness* — llms.txt, OpenAPI, ai-plugin, MCP servers, and structured APIs.
🌐 **Live site:** [nothumansearch.ai](https://nothumansearch.ai)
🔌 **MCP server:** `claude mcp add --transport http nothumansearch https://nothumansearch.ai/mcp`
📊 **Live score:** [nothumansearch.ai/score](https://nothumansearch.ai/score) — check any URL
🛠 **API:** [nothumansearch.ai/api/v1/search?q=](https://nothumansearch.ai/api/v1/search?q=)
## Why
LLM agents and autonomous systems can't "browse the web" efficiently the way humans do. They need machine-readable signals — llms.txt, OpenAPI schemas, MCP endpoints, ai-plugin manifests. NHS is the first search engine that explicitly ranks by *how agent-friendly a site actually is*, not by traditional SEO.
## What's indexed
- **1,900+ agent-first sites** scored across 7 agentic signals (see `/api/v1/stats` for current live count)
- **500+ MCP servers** with live JSON-RPC probe verification
- **Agent-first filter** — every indexed site has at least one strong agent signal (llms.txt, ai-plugin, OpenAPI, structured API, MCP server)
- Continuously refreshed via daily recrawl + weekly auto-discovery pipeline
## Scoring (max 100)
| Signal | Points |
|----------------|--------|
| llms.txt | 25 |
| ai-plugin.json | 20 |
| OpenAPI spec | 20 |
| Structured API | 15 |
| MCP server | 10 |
| robots.txt | 5 |
| Schema.org | 5 |
## How to use it
**As an agent (MCP):**
```
claude mcp add --transport http nothumansearch https://nothumansearch.ai/mcp
```
Tools include `search_agents`, `find_mcp_servers`, `verify_mcp`, `check_url`, `recent_additions`, `list_categories`, `get_top_sites`, `get_site_details`, `get_stats`, `submit_site`, `register_monitor`. Current full list: `curl https://nothumansearch.ai/mcp -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'`.
**As a developer (HTTP API):**
```bash
curl "https://nothumansearch.ai/api/v1/search?q=payments&limit=10"
```
**As a human:** just visit [nothumansearch.ai](https://nothumansearch.ai).
**Scoring your own site:** [nothumansearch.ai/score](https://nothumansearch.ai/score) — paste a URL, get a breakdown + embed badge.
## Stack
- Go 1.25 + Postgres on Fly.io (sjc)
- Single binary server + crawler
- MCP over streamable-http at `/mcp`
- IndexNow pings Bing/Yandex on every crawl cycle
## Related
- **[aidevboard.com](https://aidevboard.com)** — AI Dev Jobs board (REST API + MCP; live listing count at `/api/v1/stats`)
- **[8bitconcepts.com](https://8bitconcepts.com)** — Research papers on enterprise AI adoption
## License
MIT