Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, dete…

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

Help your LLMs online

RAG Search API

Search + Chat = SearChat(AI Chat with Search), Support OpenAI/Anthropic/VertexAI/Gemini, DeepResearch, SearXNG, Docker. AI对话式搜索引擎，支持DeepResearch, 支持OpenAI/Anthropic/VertexAI/Gemini接口、聚合搜索引擎SearXNG，…

Tiny and powerful JavaScript full-text search engine for browser and Node

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres…

Personal AI search copilot, open-source Perplexity

Vane is an AI-powered answering engine.

🔍 AI search engine - self-host with local or cloud LLMs

An AI-powered search engine with a generative UI

Perplexity Inspired Answer Engine

Building a quick conversation-based search demo with Lepton AI.

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

open-source agentic AI data assistant for the next generation of AI + Data products.

fastapi langchain javascript, streaming response 手写效果流式响应

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

🔥中文 prompt 精选🔥，ChatGPT 使用指南，提升 ChatGPT 可玩性和可用性！🚀

A close-to-metal Python API for programming AMD Ryzen™ AI NPUs (AI Engines), built on an open-source MLIR-based compiler toolchain.

Inference Llama 2 in one file of pure C++

校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

Tiny C++ LLM inference implementation from scratch

An unnecessarily tiny implementation of GPT-2 in NumPy.

Whisper is a file-based time-series database format for Graphite.

b站上的课程

Port of OpenAI's Whisper model in C/C++