Examples →

Fetch a GitHub issue or PR for an AI agent

GitHub renders issues and PRs server-side. AgentFetch's Trafilatura pass extracts the title, body, labels, and comment thread cleanly. For private repos you'll need GitHub auth — AgentFetch handles public ones out of the box.

Try it

Get a free key at agentfetch.dev (500 free fetches/mo, no credit card).

curl -X POST https://api.agentfetch.dev/fetch \
  -H "Content-Type: application/json" \
  -H "X-AgentFetch-Key: af_xxx" \
  -d '{
    "url": "https://github.com/anthropics/anthropic-cookbook/issues/1",
    "max_tokens": 2000
  }'

In an MCP-aware agent

fetch_url(
  url="https://github.com/anthropics/anthropic-cookbook/issues/1",
  max_tokens=2000,
)

In LangChain

from langchain_agentfetch import AgentFetchTool

tool = AgentFetchTool(api_key="af_xxx")
result = tool.run({"url": "https://github.com/anthropics/anthropic-cookbook/issues/1"})

How it routes

AgentFetch automatically routes fetch github issue-style URLs through Trafilatura based on domain heuristics — you don't pick a fetcher.

When agents reach for this

Triage agents, repo monitoring, code review summarization.

Related patterns

Fetch a Hacker News thread for an AI agent
Fetch a Twitter / X thread for an AI agent
Fetch a GitHub README for an AI agent
Fetch an arXiv paper for an AI agent
Fetch and extract text from a PDF for an AI agent
Fetch a public Notion page for an AI agent