Category
Research
Web, papers, knowledge graphs, citation.
17 listings
Every Research listing on ai-supply is a free, open-source AI capability that we scan and grade A–D for security before it appears here — so you can adopt with confidence, not just a star count. This category spans 4 Agents, 3 Evals, 3 MCP servers, 2 Pipelines, 2 Connectors, 1 Workflow, 1 Dataset and 1 Template.
Security posture: 6 of 17 scanned rated safe · avg score 84/100.
△평가
LM Evaluation Harness
EleutherAI's MIT-licensed unified benchmark suite — the de-facto standard for evaluating language models across 200+ tasks.
ai-supply
✓ A · 100⟳ 2mo agoguards:2
↓ 126k
◉에이전트
GPT Researcher
Autonomous AI research agent that searches the web and produces detailed, cited research reports in minutes.
ai-supply
! B · 75⟳ 10d agoshellnetworkfs
↓ 105k
△평가
OpenAI Evals
MIT-licensed framework for evaluating LLMs and AI systems — build custom evals, run model comparisons, log results.
ai-supply
✓ A · 100⟳ 3mo agoguards:4
↓ 97k
◉에이전트
STORM
Stanford's LLM-powered knowledge curation agent that researches any topic and generates a full Wikipedia-style article.
ai-supply
! B · 75⟳ 1y agonetworkfs
↓ 86k
⬡파이프라인
GraphRAG
Microsoft's graph-based RAG: build knowledge graphs from documents for global, multi-hop reasoning beyond vector search.
ai-supply
! B · 75⟳ 10d agosecretsshellnetwork
↓ 82k
◇MCP 서버
Tavily Search MCP Server
Official Tavily MCP server giving agents real-time web search, content extraction, site mapping, and crawling.
ai-supply
✓ A · 100⟳ 3d agonetworkfs
↓ 60k
◇MCP 서버
Firecrawl MCP Server
Official Firecrawl MCP server — web search, scraping to clean data, and autonomous deep research.
ai-supply
! B · 88⟳ 10mo agoshellnetworkfs
↓ 49k
◉에이전트
PaperQA2
AI agent that retrieves, reads, and synthesises answers from scientific PDFs with citation-level accuracy.
ai-supply
! B · 75⟳ 4mo agonetworkfs
↓ 47k
⌬워크플로
paperai
AI-powered literature discovery and review engine for medical and scientific papers, built on txtai semantic search.
ai-supply
✓ A · 100⟳ 1y agosecretsnetworkfs
↓ 47k
△평가
HELM — Holistic Evaluation of Language Models
Stanford CRFM's reproducible, multi-metric benchmark framework for evaluating any foundation model.
ai-supply
! B · 75⟳ 2mo agoguards:7
↓ 46k
▣데이터셋
MMLU Benchmark
MMLU: 57-subject multiple-choice benchmark for broad LLM knowledge and reasoning.
ai-supply
✓ A · 100⟳ 3y ago
↓ 44k
⇄커넥터
arxiv.py — arXiv API Python Wrapper
Pythonic client for the arXiv API: search, download, and stream 2M+ preprints by query, author, or ID.
ai-supply
✓ A · 95⟳ 2mo agonetworkfs
↓ 36k
⬡파이프라인
LightRAG
Fast retrieval-augmented generation framework that fuses knowledge-graph structure with vector retrieval.
ai-supply
! D · 58⟳ 15d agosecretsshellinstall-hook
↓ 18k
◉에이전트
ScrapeGraphAI
Prompt-driven web scraping: describe the data you want and LLM graph pipelines extract clean structured JSON from any page.
ai-supply
! B · 75⟳ 8d agoshellnetworkfs
↓ 6.8k
▤템플릿
arxiv-sanity-lite
Self-hostable web app to tag arXiv papers and get recommendations of similar papers using SVMs over tf-idf abstract features.
ai-supply
! B · 88⟳ 3y ago
↓ 6.0k
⇄커넥터
semanticscholar
Unofficial Python client for the Semantic Scholar Academic Graph APIs: papers, authors, citations, and references.
ai-supply
! B · 75⟳ 4mo agonetworkfs
↓ 3.9k
◇MCP 서버
Exa MCP Server
Connects AI assistants to Exa web search, code search, and company/deep research.
ai-supply
! B · 75⟳ 4d agonetworkfs
↓ 1.4k