Stars
A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.
microGPT benchmarks: a single M4 Max MacBook Pro P-core in C runs Karpathy's 4192-parameter transformer at ~71x the throughput of TALOS-V2's FPGA implementation.
Visual and textual documentation of 21 essential agentic design patterns for building intelligent AI systems
Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖
"Vibe-Trading: Your Personal Trading Agent"
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
OxiBonsai is a zero-FFI, zero-C/C++ inference engine for PrismML's sub-2-bit Bonsai family — both the 1-bit line (Q1_0_g128) and the ternary line (TQ2_0_g128). It runs on CPU (SIMD), Apple Silicon …
Pure Rust LLM Inference Engine — The Sovereign Alternative to llama.cpp License Rust Complete GGUF model loading, multi-format quantized inference, and an OpenAI-compatible API server — all without…
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …
The best-benchmarked open-source AI memory system. And it's free.
The agent that grows with you
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
PrismMl Bonsai vs Qwen3.5 Benchmark
Private memory for AI agents. No one should see your memories. Local-first MCP server with temporal reasoning and contradiction handling.
Open-source, customizable frontend for Venice AI. Chat, image gen, audio, video, embeddings + visual workflows — all in one UI. Your API key, your browser, no backend.
Ultra-Sparse Adaptation of 1-Bit LLMs via XOR Patches
On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.
An awesome browser extension that reads aloud webpage content with one click
Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.