Explore curated open-source engineering projects — from local AI inference frameworks and high-throughput model servers to high-performance code editors and automation runtimes. Each showcase features verified hardware specs and 3-tier setup playbooks.
Select a project domain to filter curated open-source repositories
Cloud-based Python notebook environment offering free access to NVIDIA T4 GPUs, pre-installed PyTorch/TensorFlow, and instant Google Drive integration.
A concise 1-2 sentence technical summary explaining what this tool accomplishes, why it was created, and who benefits most.
Ultra-fast code editor written in Rust, featuring 120 FPS GPU-accelerated rendering, Tree-sitter AST parsing, real-time multiplayer collaboration, and native AI completions.
Self-hosted workflow automation platform with 400+ native integrations, visual node-based graph editor, custom JavaScript/Python execution, and native LangChain AI agent nodes.
Production-grade web server and reverse proxy written in Go with automatic TLS certificate provisioning via Let's Encrypt / ZeroSSL, native HTTP/3, and clean declarative configuration.
The MIT-licensed open-source core powering Visual Studio Code — an extensible developer workbench with Language Server Protocol, integrated debugging, and Git integration.
Run open-weight LLMs like Llama 3.3, DeepSeek-R1, and Mistral locally with automatic hardware acceleration, an OpenAI-compatible REST API, and unified Modelfile management.
Datacenter-grade LLM serving framework powered by PagedAttention, continuous token-level batching, chunked prefill, and multi-GPU tensor parallelism.
Zero-dependency inference of modern transformer architectures in pure C/C++ with extreme quantization (1.5-bit to 8-bit GGUF), CPU/GPU hybrid layer offloading, and Apple Metal optimization.
No repositories found matching this filter.
Check out our dedicated VRAM Estimator and Token Cost Calculator to plan your AI infrastructure efficiently.
