PyTorch implementations of modern open-source LLM architectures (Llama, Qwen, DeepSeek, Gemma, GPT-OSS, Kimi, and more) — written from scratch for readability and learning, based on Sebastian Raschka's LLM Architecture Gallery.
☆426Sep 30, 2026Updated 3 weeks ago
Alternatives and similar repositories for OpenArch
Users that are interested in OpenArch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PSSA: a non-transformer language model written from scratch in Rust. Recurrent state-space layer, episodic memory, self-modifying weights…☆117Updated this week
- Harness Engineering 101 — building AI agents from first principles. The LLM is the brain; the harness is the body.☆605Oct 19, 2026Updated last week
- Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference…☆689Apr 16, 2026Updated 6 months ago
- litellm without the bloat☆238Updated this week
- Your local AI copilot for documents☆674Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆18Mar 3, 2026Updated 7 months ago
- Language model tokenization at GB/s☆4,137Sep 2, 2026Updated last month
- Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output,…☆714Updated this week
- Cutoffs for max. multiclass F1-score, etc.☆11Updated this week
- Shared live workspace for humans and agents — multi-pane terminals, notes, and a control plane for co-working in the open.☆20Oct 14, 2026Updated 2 weeks ago
- High-performance WebAssembly headless spreadsheet engine for web apps☆35Oct 15, 2026Updated 2 weeks ago
- You like pytorch? You like micrograd? You love tinygrad! ❤️☆30Jan 22, 2026Updated 9 months ago
- Train a tiny GPT in under a minute (CUDA only)☆56Oct 15, 2026Updated 2 weeks ago
- Independent from-scratch implementation of the Kimi K3 architecture (arXiv:2607.24653v1): KDA, NoPE, latent-space MoE, and the systems co…☆42Aug 9, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Review the Python you changed, not the Python you inherited. Git-aware AST code review that runs in the seconds before git push.☆21Oct 16, 2026Updated last week
- ☆1,471Feb 15, 2025Updated last year
- MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than let…☆81Oct 15, 2026Updated 2 weeks ago
- GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.☆126Jun 18, 2026Updated 4 months ago
- One command for file conversion: video, audio, images and docs. Wraps ffmpeg, ImageMagick, LibreOffice and pandoc, and runs offline.☆24Updated this week
- Zero-Copy Context Bridging Gateway for Multi-Agent GPU Inference. Bypasses the expensive prefill phase by dynamically stitching KV Caches…☆22Jul 25, 2026Updated 3 months ago
- Declarative terminal UI library for Lua☆64Updated this week
- A grumpy Gibson construct living in an office router. It only knows what the router can see.☆27Sep 17, 2026Updated last month
- Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data.☆1,289Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code review via the change impact measure☆69Oct 16, 2026Updated last week
- Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys…☆29Updated this week
- ☆3,432May 5, 2026Updated 5 months ago
- The Little Book of Reinforcement Learning☆1,731Jul 14, 2026Updated 3 months ago
- An open standard for portable, interoperable AI memory across tools, sessions, and devices.☆86Jul 2, 2026Updated 3 months ago
- Interactive visualization and audio exploration of drum eigenmodes. Created by Basel Ashraf.☆171Sep 3, 2026Updated last month
- An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, ha…☆51Updated this week
- Battlezone Online: a free 3D multiplayer tank game in the browser (desktop, phone or VR) that plays with BZFlag clients and servers.☆38Updated this week
- A reimplementation of Stable Diffusion 3.5 in pure PyTorch☆706Jun 14, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 🚿 타입스크립트를 위한 클린코드 - 한글 번역판 🇰🇷☆13Apr 21, 2020Updated 6 years ago
- Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, …☆1,561Oct 7, 2026Updated 3 weeks ago
- RL-training an AI agent to RL-train AI agents.☆243Jul 14, 2026Updated 3 months ago
- An open-source AI accelerator, developed by AI: RTL, ISA, simulator, compiler and profiler in one repo. Runs Qwen3, LFM2.5 and Qwen3.5 on…☆859Updated this week
- SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy …☆18Oct 21, 2026Updated last week
- ☆787Updated this week
- Keep Python on your laptop. Run PyTorch operations and hold tensors on a remote GPU, including from a Mac with no CUDA installation.☆79Oct 22, 2026Updated last week