Lists (1)
Starred repositories
the optimized, token-efficient version of the leaked Claude Fable 5 / Mythos 5 system prompt. Re-engineered into clean Markdown for universal execution on Gemini 3.1 Pro, ChatGPT 5.6, and advanced …
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
Incremental engine for long horizon agents 🌟 Star if you like it!
A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
A mood ring for text — emotion-axis readout from LLM residual streams via the Jacobian lens
Number representation when the base is a free parameter — a machine-checked corpus on function-defined radix systems, from positional notation as algebra to the geometry and conservation laws of co…
Nsight Python is a Python kernel profiling interface based on NVIDIA Nsight Tools
A holistic framework to enable the design, development, and evaluation of autonomous AIOps agents.
Parallel rsync-like pull sync over SSH with resume
Portable agent skills for use across Codex, Claude Code, and other harnesses.
1
Updated Jul 13, 2026
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
ARCHIVED — split into 6 standalone repos. See README for links.
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
slime is an LLM post-training framework for RL Scaling.
A Rust implementation of the Starlark language
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Self-contained UV scripts for data & ML tasks — OCR, vision, audio & more — run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.
💫 Toolkit to help you get started with Spec-Driven Development
Terminal Markdown previewer — GUI-like experience.
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig