mcpField
A
alpha-research

alpha-research

github.com/companion-incProductivity10.0k142 installsUpdated today
Repository

About alpha-research

alpha-research is a skill for searching, reading, and asking questions about academic papers through Feynman alpha tools or the `feynman alpha` CLI. It also supports reading paper-repository files and saving annotations.

Key features

  1. 01Semantic, keyword, and agentic paper search
  2. 02Fetch paper content or full text
  3. 03Ask questions about a paper PDF
  4. 04Read files from a paper's GitHub repo
  5. 05Save, list, and clear annotations

Use cases

  1. 01Find papers on a research topic
  2. 02Inspect a paper's methods or results
  3. 03Review source files linked to a paper
  4. 04Keep persistent notes on papers

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/companion-inc/feynman --skill alpha-research

After installing, type/alpha-researchin Claude Code to confirm it loaded.

Details

From the project README

Alpha Research CLI

Use visible Feynman alpha tools when they are available. For shell commands, use feynman alpha ...; do not call the user's bare global alpha binary because it can be stale.

Commands

CommandDescription
feynman alpha search "<query>"Search papers. Prefer --mode semantic by default; use --mode keyword only for exact-term lookup and --mode agentic for broader retrieval.
feynman alpha get <arxiv-id-or-url>Fetch paper content and any local annotation
feynman alpha get --full-text <arxiv-id>Get raw full text instead of AI report
feynman alpha ask <arxiv-id> "<question>"Ask a question about a paper's PDF
feynman alpha code <github-url> [path]Read files from a paper's GitHub repo. Use / for overview
feynman alpha annotate <paper-id> "<note>"Save a persistent annotation on a paper
feynman alpha annotate --clear <paper-id>Remove an annotation
feynman alpha annotate --listList all annotations

Auth

Run feynman alpha login to authenticate with alphaXiv. Check status with feynman alpha status.

Examples

feynman alpha search "transformer scaling laws"
feynman alpha search --mode agentic "efficient attention mechanisms for long context"
feynman alpha get 2106.09685
feynman alpha ask 2106.09685 "What optimizer did they use?"
feynman alpha code https://github.com/karpathy/nanoGPT src/model.py
feynman alpha annotate 2106.09685 "Key paper on LoRA - revisit for adapter comparison"

When to use

  • Academic paper search, reading, Q&A → Feynman alpha tools or feynman alpha
  • Current topics (products, releases, docs) → web search tools
  • Mixed topics → combine both

Comments

Markdown supported