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

39
/ 100
Emerging

# 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.

No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 14 / 25

How are scores calculated?

Stars

23

Forks

4

Language

Python

License

Apache-2.0

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.