Starred repositories
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techn…
The repository for the code of the UltraFastBERT paper
Coreference resolution for English, French, German and Polish, optimised for limited training data and easily extensible for further languages
VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social …
The best notepad for you and your agents
On-device models that know when they're wrong: every answer carries a confidence score for cloud handoff.
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
MacOS app written in Swift that bulk exports Apple Notes (including iCloud Notes) to a multitude of formats preserving note folder structure.
The Little Book of Reinforcement Learning
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
Sandbox any AI agent in seconds - zero setup, zero latency.
Implementation for Decentralized Multi-Agent Systems with Shared Context
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
Tree-sitter-powered code indexing server that gives LLM agents precise, on-demand access to symbols, implementations, callers, tests, and grep across multi-language projects - so they explore codeb…
TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.
An image-to-world skillset for Claude.
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
role-model is a protocol for assigning the right model for the right job. Use local and cloud AI together, or route between several cloud providers.
[ICML 2026] Codes of paper UniSVQ: 2-bit Unified Scalar-Vector Quantization and LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization.
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Production-grade engineering skills for AI coding agents.
Minimally lossy 2-bit post-training quantization of MoE language models using KBVQ-MoE, VPTQ
Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.