Stars
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fallback.
The highest-scoring AI memory system ever benchmarked. And it's free.
Open Claude Is Open-source coding-agent CLI for OpenAI, Gemini, DeepSeek, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.
Open-source universal artifact registry. Drop-in Artifactory/Nexus alternative with 40+ package formats, security scanning, WASM plugins, and edge replication.
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
CLI tool for configuring and monitoring Claude Code
Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
A minimal, secure Python interpreter written in Rust for use by AI
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
An open-source alternative to Claude Cowork built for teams, powered by opencode
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Transform your favorite cities into beautiful, minimalist designs. MapToPoster lets you create and export visually striking map posters with code.
Multi-agent orchestration framework powered by Pydantic AI. Build complex agent collaborations with clean, declarative code, automatic topology validation, built-in execution tracking, and full con…
A phone number can reveal whether a device is active, in standby or offline (and more). This PoC demonstrates how delivery receipts + RTT timing leak sensitive device-activity patterns. (WhatsApp /…
REAP: Router-weighted Expert Activation Pruning for SMoE compression
Comprehensive performance benchmarking suite comparing GoFlash against other frameworks
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, and unlimited context — all on Pydantic AI.