Fetch top, best or new stories from HackerNews.

Args: params (HnTopStoriesInput): - feed (str): 'top', 'best', or 'new' - limit (int): Stories to return (1–30) - min_score (int): Minimum score filter

Returns: str: JSON with feed, count, stories[]. Each story: id, title, url, score, comments, by, posted, hn_link.

Search HackerNews by keyword using the Algolia search API.

Covers all historical HN content. Find discussions on specific technologies, papers, companies, or events.

Args: params (HnSearchInput): - query (str): Search terms - limit (int): Results (1–20) - days_back (int): Recency window in days - tags (Optional[str]): 'story', 'ask_hn', 'show_hn', or empty

Returns: str: JSON with query, total_found, count, hits[]. Each hit: id, title, url, score, comments, author, posted, hn_link, excerpt.

Fetch the most recently submitted papers from arXiv AI/ML categories.

Papers appear hours before press coverage — the fastest signal of what is happening at the AI research frontier.

Categories: cs.AI (Artificial Intelligence), cs.LG (Machine Learning), cs.CL (NLP), cs.CV (Computer Vision), cs.NE (Neural Computing), stat.ML.

Args: params (ArxivLatestInput): - categories (List[str]): arXiv category codes - limit (int): Papers per category (1–20)

Returns: str: JSON with categories, total_papers, by_category dict. Each paper: id, title, abstract (400 chars), authors, published, url, pdf.

Search arXiv for papers matching a query, sorted by submission date.

Searches title, abstract and author fields. Optionally restrict to a specific AI/ML category.

Args: params (ArxivSearchInput): - query (str): Search terms (e.g. 'LLM agents tool use') - category (Optional[str]): arXiv category filter - limit (int): Papers to return (1–20)

Returns: str: JSON with query, category, count, papers[]. Each paper: id, title, abstract, authors, published, url, pdf.

Fetch the hottest stories from Lobste.rs, a curated tech community.

Lobste.rs is smaller and more technically focused than HackerNews. Invitation-only membership ensures higher signal-to-noise ratio.

Args: params (LobstersHotInput): - limit (int): Stories to return (1–25) - tag_filter (Optional[str]): Tag substring filter (e.g. 'ai', 'ml')

Returns: str: JSON with count, stories[]. Each story: title, url, score, comments, tags, submitter, submitted_at, lobsters_url.

Search GitHub for trending repositories by topic.

A surge of starred repos on a topic is a strong adoption signal. No auth required (60 req/h). Set GITHUB_TOKEN for 5,000 req/h.

Args: params (GithubTrendingAiInput): - topic (str): GitHub topic tag (e.g. 'llm', 'mcp', 'ai-agents') - limit (int): Repos to return (1–15) - min_stars (int): Minimum stars filter - sort (str): 'stars' or 'updated'

Returns: str: JSON with topic, total_found, count, repos[]. Each repo: name, description, stars, forks, language, topics, updated_at, url.

Aggregate tech & AI signals from all four sources in one call.

The primary tool for a comprehensive daily or weekly tech intelligence briefing. Combines HackerNews, arXiv, Lobste.rs and GitHub into one structured JSON digest. Use 'focus' to filter for a specific topic.

Args: params (TechSignalDigestInput): - focus (Optional[str]): Topic filter (e.g. 'MCP', 'agents') - hn_limit (int): HN stories (1–10) - arxiv_limit (int): arXiv papers (1–10) - lobsters_limit (int): Lobste.rs stories (1–10) - github_limit (int): GitHub repos (1–10)

Returns: str: JSON digest with generated_at, focus, sources{hn, arxiv, lobsters, github}. Each source has label, count, and its items list.