langgenius/dify
Dify is an open-source platform for developing and deploying AI applications using large language models, featuring workflow building, model management, agent capabilities, and observability tools.
Awesome AI Agents › AI Application Development
opral/lix
Lix is a repository backend aimed at products where both people and AI agents write files. A Lix repository holds three things in one system: files of any text or binary format, a SQL database, and version control over both. File content, application data and history live together in an ACID OLTP database that can be queried with SQL across millions of rows, and format plugins make supported file types queryable as versioned rows rather than opaque blobs. Because the change model works at that granularity, diffs name the specific clause, cell or row that changed, which makes review, merge and rollback meaningful for documents and structured data instead of only for source code. Changes are recorded without an explicit commit step, so a product can show a user a diff and offer accept or undo rather than exposing branches and pull requests. Real-time collaboration lets several people and agents share a repository and see each other's changes as they happen. Storage is pluggable: the local filesystem, IndexedDB in the browser, or S3 behind a Lix server. A JavaScript SDK is published as @lix-js/sdk with matching storage packages, a Rust quickstart exists, and Python and Go SDKs are tracked as open issues. Repositories can be opened locally against filesystem storage or in remote mode against a server URL. Documented use cases include giving every customer of a product their own repository holding their files, data and the automations an LLM writes for them, and syncing the local directories that coding agents work in so they become collaborative or cloud-backed. LixRay is the hosted offering, and a hosting guide covers running your own server. Per-file and per-group permissions are announced as planned.
Also in AI Application Development
daytonaio/daytona
Daytona is a secure and elastic infrastructure platform designed for safely running AI-generated code with high performance and scalability.
e2b-dev/awesome-ai-agents
A curated and comprehensive list of AI autonomous agents categorized into open-source and closed-source projects, serving as a valuable resource for exploring, building, and contributing to AI agent development.
mlflow/mlflow
MLflow is an open-source platform that manages the full machine learning lifecycle, providing tools for experiment tracking, model packaging, deployment, evaluation, and observability in one integrated solution.
pydantic/pydantic-ai
PydanticAI is a Python agent framework that simplifies building production-grade Generative AI applications by providing type-safe, structured, and model-agnostic integration with multiple LLMs, along with features like dependency injection and real-time debugging.
GoogleCloudPlatform/generative-ai
A comprehensive repository of sample code, notebooks, and resources for developing and managing generative AI workflows on Google Cloud using Gemini models on Vertex AI.
0xPlaygrounds/rig
Rig is a Rust library for building scalable, modular, and ergonomic fullstack agents powered by large language models, supporting multiple LLM providers and vector stores for AI integration.
mnfst/manifest
Manifest is an open-source components library built on shadcn/ui for creating customizable and production-ready UI components to develop ChatGPT and conversational AI applications efficiently.