Research & Data

🤖 Analyze fintech data with an AI Junior Data Scientist Agent that performs EDA and churn modeling, all powered by a local LLM and FastAPI.

📊 Analyze 小红书 data to uncover market opportunities and user needs, generating automated reports for business idea validation.

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

Synapse: Enterprise-grade Agentic RAG system powered by Google Gemini 3. Features self-healing retrieval (CRAG), adaptive routing, hybrid search, and multi-layer security guards for high-accuracy, production-ready AI.

🌐 Empower your AI experience with Graph-AI-Agent, a tool for synchronized knowledge management and interactive multi-agent collaboration.

🛠️ Explore and evaluate chatbot performance with this repository's tools, scripts, and metrics for intelligent payroll management systems.

🤖 Build and interact with AI models offline on Android devices using MediaPipe for seamless, on-device chat and analysis without the need for internet.

The Anti-Hallucination data layer for B2B Sourcing. Deep-verified global supply chain entities designed for RAG and LLM instruction tuning.

Agentic Q&A System leveraging LangGraph and IBM Watsonx for multi-agent orchestration. Features autonomous routing, reflection loops, and self-correction to ensure verified outputs. Includes high-fidelity parsing via Docling and hybrid retrieval (BM25 + ChromaDB) for sophisticated, enterprise-ready document intelligence.

Fancy stream processing made operationally mundane

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Data infrastructure for AI

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

Exa MCP for web search and web crawling!

Catalog of official Microsoft MCP (Model Context Protocol) server implementations for AI-powered data access and tool integration

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

Agent OS integrations for deployed agents and swarms: execute-first routing, Micro ECF harness exports, x402 edge calls, receipts, and USDC settlement on Base.

Codex skill for DataSuite failure alert diagnosis and approved reruns with local TSV audit logging.

Claude Code and Codex skill for the targets R package (targets >= 1.12). Modern patterns for reproducible analysis pipelines.