Infrastructure Open-Source Projects

Showing 40 indexable projects from the current snapshot.

• usestrix/strix

  Strix provides autonomous AI penetration testing agents that dynamically execute code and validate vulnerabilities with working proofs-of-concept. Teams must have Docker running and provide an LLM API key from a supported provider to opera…

• diegosouzapw/OmniRoute

  A self-hosted AI gateway that aggregates 250+ providers into a single endpoint with auto-fallback routing and token compression. It is suited for developers and AI engineers who need to consolidate multiple API keys, manage rate limits, an…

• openai/whisper

  Whisper is a general-purpose speech recognition model that performs multilingual transcription, speech-to-English translation, and language identification. It replaces many stages of a traditional speech-processing pipeline using a single…

• tensorflow/tensorflow

  TensorFlow provides an end-to-end open source machine learning platform with tools and libraries for building and training ML models. It supports CPU and GPU execution across Linux, macOS, Windows, Android, and Raspberry Pi, and can be ins…

• vllm-project/vllm

  vLLM provides high-throughput, memory-efficient inference and serving for large language models. It targets developers who need to serve models locally or in self-hosted environments with efficient attention memory management.

• ggml-org/llama.cpp

  llama.cpp is a dependency-free C/C++ library for running large language model (LLM) inference locally or in the cloud. It provides tools for model quantization, grammar-constrained generation, and API serving, requiring models to be in the…

• BerriAI/litellm

  LiteLLM provides a unified gateway and Python SDK for calling 100+ LLM providers using the OpenAI format, addressing the operational complexity of managing disparate SDKs and authentication patterns. It includes production-ready features s…

• supabase/supabase

  Supabase provides an open source, Firebase-like developer experience built around a dedicated Postgres database for web, mobile, and AI applications. It integrates database, authentication, and storage services, supporting self-hosted or m…

• pytorch/pytorch

  A Python library providing GPU-accelerated tensor computation and a dynamic neural network framework built on a tape-based autograd system. It is designed for researchers and developers who require flexibility and speed for deep learning m…

• qdrant/qdrant

  A vector similarity search engine that stores, searches, and manages dense, sparse, and multi vectors with attached JSON payloads for AI and semantic matching applications. It is written in Rust and provides extended filtering, distributed…

• langfuse/langfuse

  An open-source platform that helps teams collaboratively observe, evaluate, and debug LLM calls. It provides tracing, prompt management, and testing capabilities for AI engineering workflows.

• codecrafters-io/build-your-own-x

  A curated compilation of links to step-by-step tutorials for recreating popular technologies from scratch. It serves as a directory for developers and educators to find resources on building systems such as databases, operating systems, an…

• karpathy/autoresearch

  This project provides an autonomous research loop where an AI agent modifies training code, runs short experiments, evaluates results, and iterates automatically to improve a small LLM. It requires a single NVIDIA GPU and uses a fixed 5-mi…

• opencv/opencv

  OpenCV is an open-source library that provides algorithms and functions for computer vision, deep learning, and image processing. It operates locally as a dependency, handling image and video inputs to produce processed media and feature d…

• PaddlePaddle/PaddleOCR

  PaddleOCR converts PDF documents, images, and Office files into structured formats including JSON, Markdown, and DOCX. The project features PaddleOCR-VL-1.6, a 0.9B parameter vision-language model, alongside PP-StructureV3 layout conversio…

• earendil-works/pi

  A self-hosted coding agent and CLI framework that unifies multiple hosted LLM APIs (OpenAI, Anthropic, Google) into a single interface. Requires external API credentials and lacks a built-in permission system, making external sandboxing ne…

• netdata/netdata

  Netdata provides per-second, real-time infrastructure monitoring with auto-discovery and zero configuration. It is self-hosted, operates with low resource overhead, and includes edge-based ML anomaly detection.

• bytedance/deer-flow

  An open-source agent harness that orchestrates sub-agents, long-term memory, and sandboxed execution to perform complex, long-horizon tasks such as research, coding, and content creation.

• binhnguyennus/awesome-scalability

  This project is a curated reading list that links to articles, engineering talks, and case studies explaining how to design scalable, reliable, and performant large-scale systems. It serves as a reference resource for developers and resear…

• OpenBB-finance/OpenBB

  OpenBB provides a connect-once infrastructure layer that consolidates proprietary, licensed, and public financial data for consumption across Python environments, OpenBB Workspace, Excel, REST APIs, and MCP servers for AI agents.

• labmlai/annotated_deep_learning_paper_implementations

  A collection of simple PyTorch implementations of neural networks and related algorithms, rendered as side-by-side formatted notes to aid reader comprehension. It addresses the difficulty of understanding deep learning papers by providing…

• xtekky/gpt4free

  This project aggregates multiple LLM and media generation providers behind a unified OpenAI-compatible interface. It provides Python and JavaScript clients, a local GUI, a REST API, and an MCP server under a community-first license.

• songquanpeng/one-api

  This project consolidates API keys and distributes LLM API requests across multiple model providers using a standard OpenAI-compatible API format. It provides load balancing across configured channels.

• tldraw/tldraw

  tldraw is an extensible React SDK for building infinite canvas applications, providing programmable drawing, shapes, and real-time collaboration. It requires a React development workflow and mandates a paid license for production use.

• JuliaLang/julia

  Julia is a high-level, dynamic programming language designed for technical computing, combining ease of use with high performance for numerical and scientific tasks. It runs on cross-platform systems via local binaries or source builds.

• Lordog/dive-into-llms

  A free, hands-on LLM programming tutorial series derived from Shanghai Jiao Tong University courses, covering topics from fine-tuning to AI agents. It provides slides, guides, and Jupyter notebooks for learners who want practical experienc…

• apache/airflow

  Apache Airflow is a platform for authoring, scheduling, and monitoring workflows as code. It targets data teams that need to orchestrate tasks and data pipelines, but does not provide native Windows support or handle streaming workloads.

• Kong/kong

  Kong is a cloud-native, platform-agnostic gateway designed to orchestrate microservices, conventional API traffic, and agentic LLM and MCP traffic. It provides centralized proxy functionality, AI governance, and extensible deployment model…

• QuantumNous/new-api

  A large language model gateway and asset management system that aggregates OpenAI, Claude, and Gemini APIs behind a unified interface. It provides format cross-conversion, channel routing with retry logic, and per-request billing for teams…

• ray-project/ray

  Ray provides a unified framework for scaling Python and AI applications from a laptop to a cluster. It offers distributed abstractions for tasks and actors, alongside libraries for data processing, training, tuning, reinforcement learning,…

• deepspeedai/DeepSpeed

  DeepSpeed is a PyTorch-integrated library that applies system innovations such as ZeRO, ZeRO-Infinity, 3D-Parallelism, and Ulysses Sequence Parallelism to make large-scale deep learning training and inference more efficient and effective.

• hpcaitech/ColossalAI

  ColossalAI provides parallel components that let developers write distributed deep learning models for training and inference with reduced hardware constraints. It targets AI engineers and researchers working on Linux systems with NVIDIA G…

• pingcap/tidb

  TiDB is an open-source, cloud-native distributed SQL database that handles transactions, analytics, and vector search. It provides horizontal scalability and MySQL compatibility while maintaining ACID guarantees across multiple nodes.

• google-ai-edge/mediapipe

  MediaPipe provides cross-platform libraries and tools for building and deploying on-device machine learning pipelines that process images, video, and text locally on the user's device. It is intended for developers who need to integrate cu…

• 1Panel-dev/1Panel

  1Panel is a web-based VPS control panel that enables server and Docker management through a visual GUI, replacing the need for CLI memorization. It natively integrates an AI agent runtime for deploying LLMs and includes an app marketplace…

• musistudio/claude-code-router

  Claude Code Router is a local control plane that exposes one stable endpoint for routing requests across multiple LLM providers and coding agents. It consolidates provider credentials, routing rules, and observability into a single self-ho…

• Arize-ai/phoenix

  Open-source AI observability and evaluation platform for LLM applications. Provides OpenTelemetry-based tracing, LLM evaluation, versioned datasets, and experiment tracking.

• lllyasviel/ControlNet

  lllyasviel/controlnet is a neural network structure for controlling text-to-image diffusion models by adding extra spatial conditions. It learns conditional control on small datasets using zero convolution layers, without destroying the or…

• alibaba/nacos

  Nacos provides dynamic service discovery, dynamic configuration management, and service management for microservices platforms. It is intended for developers and operations teams building cloud native applications.

• datawhalechina/happy-llm

  A free, open-source tutorial that teaches large language model principles by covering architecture, pre-training, fine-tuning, and applications. It guides learners through building a LLaMA2 model from scratch using PyTorch.