Tag

Qlib is an open-source, AI-oriented quantitative investment platform from Microsoft that provides a full pipeline for quant research — data processing, feature engineering, model training, backtesting and serving. It supports supervised learning, market-dynamics modeling and reinforcement learning, and integrates tools (e.g., RD-Agent) for automated factor mining and model optimization.

Pathway is a Python ETL and live data framework combining a user-friendly Python API with a high-performance Rust engine. It supports both batch and streaming pipelines, stateful transformations, persistence, numerous connectors, and includes LLM/RAG tooling for real-time analytics and live LLM pipelines.

Activepieces is an open-source business automation tool that serves as an alternative to Zapier, emphasizing AI integrations. It enables the creation of AI agents, workflows, and MCP servers using a type-safe TypeScript framework, with over 280 community-contributed pieces, AI-first features, and self-hosted deployment for security.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs. It offers a streamlined RAG workflow adaptable to enterprises of any scale. Powered by a converged context engine and pre-built agent templates, RAGFlow enables developers to transform complex data into high-fidelity, production-ready AI systems with exceptional efficiency and precision.

Ragas is an open-source toolkit by VibrantLabs for evaluating and optimizing large language model (LLM) applications. It offers objective metrics (LLM-based and traditional), automated test-data generation, integrations with popular LLM frameworks and observability tools, and utilities for building feedback loops to improve production LLMs.

BISHENG is an open LLM application DevOps platform for enterprise AI applications. It provides GenAI workflows, RAG, agents, unified model management, evaluation, SFT, dataset management, enterprise-grade system management and observability. Key strengths are a powerful visual workflow/orchestration system (with loops, parallelism, human-in-the-loop), high-precision document parsing, and features targeted at production enterprise deployments.

Claude-Mem is a persistent memory compression system built for Claude Code. It automatically captures tool usage observations during coding sessions, generates semantic summaries using Claude's agent-sdk, and injects relevant context into future sessions to maintain continuity of project knowledge.

Daytona is a secure and elastic infrastructure for running AI-generated code. It provides fast, isolated sandboxes (sub-90ms creation), SDKs for Python and TypeScript, programmatic control (file, Git, LSP, execute APIs), OCI/Docker compatibility, and persistent sandboxes. Designed to safely execute model-generated or untrusted code at scale, Daytona emphasizes isolation, performance, and developer-friendly APIs. It is open-source under the AGPL-3 license.

Refly.AI is the world's first vibe workflow platform for non-technical creators, enabling them to build, share, and monetize powerful AI automation workflows using simple prompts and a visual canvas—no coding required. It simplifies automation like N8N for non-tech users and Canva for workflows.

Supermemory is a high-performance, scalable memory engine and web app that acts as an AI “second brain”. It provides a Memory API and user-facing apps/extensions to save content (links, PDFs, text), perform semantic retrieval, and chat with your saved memories. It integrates with major AI tools via an MCP layer, offers browser and Raycast extensions, developer console and self-hosting options for enterprise deployment.

Supermemory is a memory engine and application that provides a fast, scalable Memory API for saving, organizing, and retrieving personal or team knowledge. It supports adding content from URLs, files, and text, enables conversational access to stored memories, and integrates with major AI tools and browser extensions.

Kortix (suna) is a full platform for building, managing and training autonomous AI agents. It offers an agent builder, browser automation, file and data management, web intelligence, system operation tools, and integrations with LLM providers (OpenAI, Anthropic, LiteLLM). It supports self-hosting and scalable agent runtimes.