balajivis/sutra-mas
36,299 multi-agent systems papers collected, 17,969 analyzed with coordination patterns, embeddings, and a 16-cluster taxonomy — the largest structured MAS corpus bridging 30 years of classical research with modern LLM agents
# Technical Summary The corpus pairs 17,969 deep-analyzed papers with extracted coordination patterns (blackboard, contract net, BDI, stigmergy, etc.), UMAP embeddings, and 16-cluster taxonomy enabling structured queries like "blackboard papers that don't cite Nii 1986." Built via an 8-agent LLM pipeline, it includes ~100K directed citation edges, classical-to-modern "Rosetta Stone" mappings, and a "Lost Canaries" dataset identifying high-citation classical work with near-zero modern adoption. The data spans four sources (ArXiv, OpenAlex, DBLP, Crossref) with per-paper metadata including theoretical grounding, cluster assignment, and 2D UMAP coordinates for visual exploration.
Stars
23
Forks
4
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/balajivis/sutra-mas"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
matte1782/lecture-mind
VL-JEPA Lecture Summarizer - Event-aware lecture summarization using vision-language understanding
ISDO-TUM/Capstone-2025
AI-Agent powered academic paper discovery engine
Atik203/Scholar-Flow
ScholarFlow is a SaaS platform designed for researchers, students, professors, and academic...
sanketjadhav09/ClearClause-Legal-AI-Assistant
ClearClause: A Legal AI Assistant using Google Gemini API for QnA, summaries, translations, and...
smsharma/AIrXiv
AI-powered arXiv research assistant prototype.