Paper Scout
Find and verify real research papers through a keyless index — no login or API key from a normal IP. Search by topic or method, map a field's citation graph, pull the in-body passages that prove a claim, or scan GitHub for engineering prior art. Grounds every answer in papers the index actually returns — never invents titles or arXiv IDs.
About
Agents hallucinate citations. Paper Scout reads the papers first.
Five moves over one keyless index: `search` (semantic search over abstracts), `similar` (turn one hit into its family — references, citers, or neighbours), `inspect` (canonical metadata for one paper), `read` (the in-body passages that answer a specific question — this is how you verify), and `github` (issues / PRs / READMEs for engineering prior art).
Six use cases: find the paper, map a field or related-work, ground a claim before you assert it (the anti-hallucination move for any writing agent), find prior art, scan what's new, and build a reading list — references are the prerequisites, citers are the frontier.
Honest by construction: stdlib Python, one file, no dependencies. It returns only ids, titles, and numbers the index actually returned — never an invented arXiv id. Passages come back scored, and a low score is treated as unconfirmed, not laundered into a citation. When the index can't answer, `search` degrades out loud to the public arXiv API with a stderr banner; the other moves print the error instead of guessing.
Keyless from a normal IP. The research index answers over plain HTTP — no login, no API key — capped per IP per day. From a datacenter or agent host it may return a 403 and ask for a key; set the free FIRECRAWL_API_KEY env var (no card) and the script adds it automatically. Optional, never a paywall. Data backend is Firecrawl's public research index — the skill, method, engine, and voice are Solid State's own.
A daily investor-grade briefing on SpaceX (now public as SPCX, merged with xAI). Live X + web search across the stock, Starlink, and the xAI/Grok AI segment — with Nasdaq/Yahoo analyst targets, SEC filings, and Kalshi prediction-market odds — distilled into a tight, price-moving, sourced brief.
Surface profitable affiliate sub-niches scored by commission rate, SERP gap, trend slope, and content difficulty.
Fair, structured 1v1 comparison between two AI tools. Pricing, features, real-world performance, switching cost, who-it's-for.