Repository Index

Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads a step ahead. Mac, iPhone, Android, Windows.

• edge-ai
• foundation-model
• on-device-ai

Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 50 other agents.

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

• apple-silicon
• local-llm
• macos
• mlx

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

TokenSpeed is a speed-of-light LLM inference engine.

• deepseek
• kimi
• lightseek
• llm

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

• graph-structures
• graphs
• large-language-models
• llm

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.

• agent-plugin
• claude-code
• codex
• cursor

UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.

• machine-learning
• experimentation
• llm-prompting
• llm-test

I made my AI think harder by making it argue with itself repeatedly. It works stupidly well.

Extract structured data and insights from documents using LLMs and decision models

• ai
• data-extraction
• document-intelligence
• generative-ai

Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"

⚠️ Experimentelle Skill-Sammlung für deutsches Recht (Arbeits-, Gesellschafts-, Insolvenz-, Datenschutz-, Prozessrecht u.a.) – inzwischen verbessert und im Alltag getestet, aber weiterhin Experiment. Bitte selber ausprobieren, Issues/PRs willkommen! Keine Rechtsberatung. Mandatsgeheimnis (§§ 203/204 StGB, § 43e BRAO), DSGVO, US-Transfer, KI-VO & Co

• anthropic
• bgh
• claude-skills
• dsgvo

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

• agents
• calibration
• classification
• decision-making

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

• natural-language-generation
• natural-language-processing
• nlg
• nlp

Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'

Scaling in Games: Continued Pre-Training for Embodied Agents in Diverse Virtual Worlds. Weights on Hugging Face.

• embodied-agent
• game-agent
• game-ai
• mihoyo

JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.

• agent-skills
• calibration
• claude-code
• decision-model