Research & Data

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

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.

Claude Code plugins and Codex skills from Calif.io for AI-assisted security research and code auditing

AI agent skill: automated real estate listing sync from Idealista to Notion database

Collection of AI Agents, Skills, and their Metadata.

Explains automated tests in business language and reviews automation quality, coverage, and traceability.

Generates realistic synthetic datasets for tests and demos with seeded, locale-aware, and distribution-shaped data.

Turns raw product requirements into testable acceptance criteria, coverage notes, and machine-readable contracts.

Prompt-first Codex skill that turns external repos into analysis specs, migration packs, and targeted internalization work.

A Claude Code skill that removes AI writing patterns from text. 32 patterns, 3 hard constraints, research-backed.

🦞+🔬: NanoResearch: The Autonomous AI Research Assistant