Awesome Chatgpt

Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

OpenLIT is the open-source agent harness engineering platform: trace, evaluate, guard, and improve everything around the model in your AI agents, on OTEL.

LLM speculative inference server for heterogeneous hardware & consumer GPUs

Turn expensive prompts into cheap fine-tuned models

QuantMind is an agent-native knowledge extraction and retrieval framework for quantitative finance.

Community maintained hardware plugin for vLLM on Ascend

Concatenate a directory full of files into a single prompt for use with LLMs

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

NOF0 - 开源的 AI 交易竞技场

All-in-one platform for search, recommendations, RAG, and analytics offered via API

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

dLLM: Simple Diffusion Language Modeling

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

A AI general-purpose state-space search engine, validated first on autonomous penetration testing.

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.

A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.

Build, run and scale AI agents like API and microservices

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.

A benchmark for LLMs on complicated tasks in the terminal

AudioMuse-AI uses sonic analysis to rediscover forgotten songs, uncover hidden connections in your music library, and generate intelligent playlists for Navidrome, Jellyfin, LMS, Lyrion, Emby and Plex: no metadata or external services required.

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

Data-centric LLM training with dynamic sample selection, domain mixture optimization, and example reweighting inside the LLaMA-Factory training loop.

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.

Auto-GPT中文版本及爱好者组织 同步更新原项目 AI领域创业 自媒体组织 用AI工作学习创作变现

the terminal client for LLMs

A simple, performant, and scalable Jax LLM!

SDG is a specialized framework designed to generate high-quality structured tabular data.

A Lightweight LLM Post-Training Library

Seamlessly integrate LLMs as Python functions

The SOTA Open-Source Browser Agent for autonomously performing complex tasks on the web

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

Doing simple retrieval from LLM models at various context lengths to measure accuracy

Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems.

Translate full-length books and documents with Ollama, OpenAI-compatible, Gemini, Mistral, DeepSeek, Poe or OpenRouter. Preserves formatting. Resumes where you left off. No file size limits.

🤖Self-Modifying Framework from the Future 🔮 World's First AMS

Label, clean and enrich text datasets with LLMs.

LangServe 🦜️🏓

GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

ChatGPT Plus/Team/Pro 订阅协议端到端重放工具集 · hCaptcha 视觉求解器 · 反欺诈机制实证研究 / End-to-end protocol replay toolkit for ChatGPT Plus/Team/Pro subscription with from-scratch hCaptcha solver and empirical anti-fraud research

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

Endurain is a self-hosted fitness tracking service designed to give users full control over their data and hosting environment

Unofficial API Wrapper for Perplexity.ai + Account Generator with Web Interface

A robust, all-in-one GPT interface for Discord. ChatGPT-style conversations, image generation, AI-moderation, custom indexes/knowledgebase, youtube summarizer, and more!

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

Continual learning infra for self-improving agents

Korea Investment & Securities Open API Github