Open Source Frameworks
Discover 104 open source Framework repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Framework projects here are most often combined with Python, LLM and AI Agents. Last updated October 4, 2026.
104 repositories · updated October 4, 2026
picotron: Train Llama-Like Models with Distributed Parallelism
Picotron is a compact Python framework for learning and experimenting with distributed pre-training of Llama-like models. It demonstrates data, tensor, pipeline, and context parallelism, prioritizing readable code over peak performance.
sqlmodel: Build Python Models for SQL Databases
SQLModel combines Pydantic-style data models with SQLAlchemy database mapping in one Python library. It suits FastAPI developers and Python teams who want typed models for validation and database access without maintaining duplicate definitions.
mcp-agent: Build Agents with Model Context Protocol
A Python framework for building LLM agents around Model Context Protocol servers and composable workflow patterns. It suits developers who need MCP integrations, multi-agent workflows, or durable execution with Temporal.
video.js: Add a Web Video Player to Your Site
Video.js is a JavaScript player and framework for adding video playback to websites. It supports common web media formats, including HLS and DASH, and can be customized with options and plugins.
react-admin: Build API-Backed Admin Applications
react-admin is a TypeScript and React framework for building browser-based administration apps on REST or GraphQL APIs. It provides reusable CRUD interfaces and customizable components, making it useful for teams that need an admin UI without building its foundations from scratch.
KAG: Build Knowledge-Grounded Reasoning and Q&A Systems
KAG is a Python framework for building domain-specific question-answering systems that combine knowledge graphs, source text, and LLMs. It targets factual and multi-hop reasoning where vector similarity alone may be insufficient.
ohmyzsh: Customize and Manage Your Zsh Configuration
Oh My Zsh is a community-driven framework for customizing zsh with plugins, themes, aliases, and update tools. It suits terminal users who want a configurable shell without building every enhancement themselves.
trident: Fuzz Test Solana Programs
Trident is a Rust framework for fuzz testing Solana programs through guided, stateful transaction sequences. It helps Solana developers and auditors explore edge cases and check program behavior beyond conventional unit tests.
ROMA: Build Hierarchical Multi-Agent Systems
ROMA is a Python framework for solving complex tasks through recursive planning and coordinated agents. It suits developers building extensible multi-agent workflows with LLMs, tools, and optional persistence or API services.
txtinstruct: Build Instruction-Tuned Models from Your Data
txtinstruct is a Python framework for creating instruction-following datasets and training instruction-tuned models. It is intended for people who want greater control over dataset licensing or to incorporate their own data.
dioxus: Build Cross-Platform Apps with Rust
Dioxus is a Rust UI framework for building web, desktop, and mobile apps from a shared codebase. It combines reactive UI, development tooling, and optional fullstack features for teams that want Rust across client and server.
mlx-examples: Explore Machine Learning Models with MLX
A collection of standalone Python examples for the MLX machine learning framework, spanning language, image, video, audio, and multimodal models. Use it to learn MLX or adapt example implementations for experiments on supported hardware.