A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Repository Index
111,085 visible repositories in the index
1–15 of 15 · Most stars
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Robust recipes to align language models with human and AI preferences
- llm
- rlhf
- transformers
Copy-ready prompts for the leading AI video and image models, each with its real output and source. Plus agent recipes for editing video.
- awesome
- awesome-list
- agents
- ai-video
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, sglang, llama.cpp and other custom engines) and model-agnostic. Currently shipping Qwen3.8-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×/2×/4x/8x cards.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Recipes to train reward model for RLHF.
DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
- agent-architecture
- ai-agents
- ai-education
- ai-from-scratch
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- llms
- mechanism
- on-policy-distillation
⛔ No longer maintained → dev-agent-kit/recipes 让 Claude Code、Antigravity、Gemini CLI、Codex、Cursor 开箱即用的分层配置模板,总结十多年的日常开发经验
- claude-code
- codex
- gemini-cli
- cursor
RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
- chromadb
- information-retrieval
- openai
- python
NEO Series: Native Vision-Language Models from First Principles
- agi
- encoder-free-vlm
- large-language-models
- multimodal
A production-grade, high-efficiency Agentic RL framework for frontier LLMs with validated recipes.