⚡️ Fast and lightweight malware scanner written in go.

Generate images of code and terminal output 📸

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Language model tokenization at GB/s

Up to 3× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3, Ornith-1.0, ternary Bonsai-27B.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

Core ecosystem — go-inference

A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official (NV)FP4 checkpoint's quality on consumer Blackwell cards

Core ecosystem — go-i18n

Core ecosystem — Go DI framework

Open source observability platform for logs, metrics, traces, frontend monitoring, pipelines and LLM observability. A sophisticated, simple and highly performant alternative to Datadog, Splunk, and…

Adversary Emulation Framework

Integrated sandbox for coding agents. Browser, dependencies, dev server, and workspace in one disposable environment. Local-first. No hosted sandbox. No SaaS account required.

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

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.

Runs 405B LLMs on 8GB VRAM

Skills for the Gemma and model/agent interactions

Multilingual Reasoning Gym enables the procedural generation of perfectly parallel multilingual reasoning datasets

AI Infrastructure Engineer Learning Track - Production ML infrastructure curriculum (2-4 years experience)

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

The safest, simplest way to manage Hermes from your Mac. Pure SSH. No gateways, no exposed ports, no browser layer.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Starlark in Go: the Starlark configuration language, implemented in Go

A library that provides an embedded python distribution to be usable from inside golang