Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Repository Index
47,133 repositories indexed
1–24 of 38 · Most stars
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
- knowledge-graph
- large-language-models
- retrieval-augmented-generation
- genai
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
TranslatedLangchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
- chatglm
- langchain
- llm
- knowledge-base
Topic Modelling for Humans
- gensim
- topic-modeling
- information-retrieval
- machine-learning
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
TranslatedOpen-source manuscript of 《深入理解 AI Infra：量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
- accelerator
- ai-infra
- ai-infrastructure
- book
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
TranslatedTencent CodeBuddy account pool management console with a built-in OpenAI-compatible reverse proxy gateway: bulk onboarding of accounts via QR code scan, scheduled check-ins and keep-alive, key grouping and distribution, IP and model whitelists, call logs and usage statistics; supports one-click updates with signature verification.
- account-manager
- api-gateway
- codebuddy
- fastapi
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.
Run many AI agents at once on your Mac, up to 3x faster.
- agents
- apple-silicon
- artificial-intelligence
- inference-acceleration
Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode
TranslatedAn AI avatar for real-time voice/text conversations with idols from "The iDOLM@STER Shiny Colors": original Japanese voice + Chinese subtitles, recalling the original story, memory shared across characters; supports Google/GitHub login and bring-your-own key, one-command deployment with Docker Compose (inspired by LAPLACE Eidolon)
- ai-companion
- character-ai
- fastapi
- idolmaster
Our lightning-fast inference engine.
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
- calibration
- cuda
- cuda-graphs
- decision-making