Lists (1)
Starred repositories
Bend 2: a fast language that blocks AI mistakes via proof. Install: curl -fsSL https://bend-lang.com/install.sh | sh
Brig: run coding agents in a microVM sandbox - the Go cli (brig) and session daemon (brigd)
One llama.cpp flag unlocks +33-39% decode speed for Qwen3.8-27B on consumer GPUs. The MTP head already ships inside your GGUF. Recipe, paired benchmarks, probe tool.
cut Claude Code token usage by rendering text context as images
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.
MiniCPM5: SOTA on-device LLMs, small yet powerful.
A curated list of best cuda programming books
MiniMax M2.7 NVFP4 dual-GB10 Blackwell benchmark: vLLM FlashInfer-CUTLASS, public data, HTML canvas report, and Docker runtime.
Rust implementation of behavior trees for deterministic AI (now with Python bindings)
Pachtop - a more modern system monitor 🚀
Open-source desktop SQL workspace with 3 built-in database drivers and 16 shipped plugins, including SQL Server, DuckDB, ClickHouse and Redis. Built-in MCP server for Claude, Cursor and Devin, SQL …
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
All Stanford Cheatsheets: Artificial Intelligence, Transformers, LLMs, Deep Learning, Machine Learning, Probabilities, Statistics, Algebra and Calculus.
Curated list of datasets and tools for post-training.
Programmable chat templates for LLM training and inference.
This Repository Contain All the Artificial Intelligence Projects such as Machine Learning, Deep Learning and Generative AI that I have done while understanding Advanced Techniques & Concepts.
Algebrica is free and open a mathematical knowledge base dedicated to clarity, structure, and conceptual coherence.
cuda-oxide is a Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, ju…
Rust By Practice will evolve into Origin.
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Master programming by recreating your favorite technologies from scratch.
Can Language Models Rebuild Programs From Scratch?
SPECA: Specification-to-Checklist Agentic Auditing Framework
A Minimalist, Batteries-included Repository for Advancing World Model Science.