shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities →
“Fuzzy title match (0.73): “When Structured Sparse Autoencoders Learn Consistent Concept” ≈ “shareAI-lab/learn-claude-code””
- FuzzySimilar title/name (fuzzy) · 59%Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning →
“Fuzzy title match (0.73): “Before Thinking, Learn to Decide: Proactive Routing for Effi” ≈ “shareAI-lab/learn-claude-code””
- FuzzyOverlapping authors or contributors · 62%A VLM-Enhanced Framework for Comprehensive Traffic Sign Condition Assessment Integrating Daytime Visual Performance and Nighttime Retroreflectivity Evaluation →
“Shared author/contributor keys: yue”
- LinkedLinked via dependency parse · 85%anthropic →
“Listed in requirements.txt”
- LinkedLinked via dependency parse · 85%python-dotenv →
“Listed in requirements.txt”
- LinkedLinked via dependency parse · 85%pyyaml →
“Listed in requirements.txt”
- FuzzySimilar title/name (fuzzy) · 59%Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled →
“Fuzzy title match (0.73): “Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled” ≈ “shareAI-lab/learn-claude-code””
- LinkedLinked via github contributor · 85%Bill-Billion →
“51 commits”