youngfly93

youngfly93 / biocli

Public

Agent-first bioinformatics CLI: query NCBI/UniProt/KEGG/STRING/Ensembl/Enrichr, download data, prepare research-ready directories

agent agent-first ai-agent bioinformatics claude-code
12
0
100% credibility
Found Apr 09, 2026 at 12 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

biocli is a command-line tool that lets users query multiple biological databases like NCBI, UniProt, KEGG, and STRING with simple commands and agent-friendly structured output.

How It Works

1
🔍 Discover biocli

You hear about biocli from a biology friend or online forum as a simple way to quickly grab gene info, papers, and datasets without endless browser tabs.

2
đź“Ą Get biocli on your computer

You follow the easy instructions to add biocli to your computer—it takes just a minute and needs no special setup.

3
âś… Check it's ready

You run a quick test command and see everything lights up green, confirming biocli can reach biology databases right away.

4
🔬 Ask about a gene

You type a gene name like TP53 and instantly get a full report with its function, pathways, partners, and recent papers.

5
🚀 Run a smart workflow

For bigger questions, you scout datasets or prepare a project folder—biocli handles multiple databases at once and builds everything you need.

🎉 Your biology data is ready

You now have clean, organized results to explore, share, or feed into your analysis—no more tab chaos or manual copying.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 12 to 12 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is biocli?

biocli is an agent-first bioinformatics CLI built in TypeScript that lets you query NCBI, UniProt, KEGG, STRING, Ensembl, and Enrichr from the terminal, download datasets like GEO/SRA FASTQs, and prepare research-ready directories with manifests. One command like `biocli aggregate gene-dossier TP53` pulls gene summaries, pathways, interactions, literature, and variants in parallel, outputting structured JSON that replaces juggling browser tabs. It handles 55 commands across these databases plus ProteomeXchange/PRIDE and a local Unimod PTM dictionary.

Why is it gaining traction?

It stands out with agent-first design—self-describing schemas via `biocli list -f json`, consistent result envelopes, and batch input—making it ideal for AI agents like Claude or Cursor without custom wrappers. Benchmarks show 88% workflow coverage at 100% quality (vs. BioMCP's 24%), plus downloads and directory prep no other CLI matches. The strict JSON contract and 24-hour cache keep outputs reliable and fast.

Who should use this?

Bioinformatics grad students or postdocs tired of scripting NCBI/UniProt/KEGG lookups for gene dossiers or variant reports. Proteomics researchers scouting PTM datasets across ProteomeXchange/PRIDE. Developers building AI agents that need structured bio data without HTML scraping.

Verdict

Try it for agent-first bioinformatics workflows—docs and benchmarks are strong despite 12 stars and 1.0% credibility score signaling early maturity. Solid for retrieval and prep, but watch for stability as adoption grows.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.