Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.
Repository Index
132,241 visible repositories in the index
1–19 of 19 · Most stars
SGLang is a high-performance serving framework for large language models and multimodal models.
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
- ai
- python
- natural-language-processing
- react
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
- metric-learning
- deep-learning
- computer-vision
- machine-learning
OpenClaw-RL: Train any agent simply by talking
- async
- memory-systems
- open-claw
- openclaw-skills
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
- large-language-models
- video-language-pretraining
- vision-language-pretraining
- blip2
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.
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
- eagle
- eagle3
- pytorch
- sglang
Understanding R1-Zero-Like Training: A Critical Perspective
- llm
- r1-zero
- reasoning
- rl
Reinforcement Learning via Self-Distillation (SDPO)
- distillation
- llm
- reasoning
- rl
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts
Open multimodal decision models, 0.8B to 27B, for text, images and video. Decide with probabilities over your own candidates and locate with bounding boxes, in place of generated text. Free API, ONNX, GGUF, vLLM and SGLang; fine-tuning code included.
- decision-model
- jev
- system-one
- typed-decisions
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
- adan
- bert-model
- convnext
- deep-learning
One API for all LLMs either Private or Public (Anthropic, Llama V2, GPT 3.5/4, Vertex, GPT4ALL, HuggingFace ...) 🌈🐂 Replace OpenAI GPT with any LLMs in your app with one line.
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
- alignment
- dpo
- llm
- llm-aligment
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.