litgpt
LitGPT is a high-performance framework for pretraining, finetuning, and deploying over 20 popular LLMs with minimal abstraction for maximum control and scale.
RD-Agent
R&D-Agent is a multi-agent framework that automates the industrial R&D process for data-driven scenarios, specializing in machine learning engineering, quantitative finance, and data science.
Vibe-Trading
Vibe-Trading is an AI-powered trading agent framework that automates the entire pipeline from investment hypothesis and market data analysis to backtesting and live execution.
casdoor
Casdoor is an AI-first Identity and Access Management (IAM) platform and MCP gateway that provides a centralized server for authentication and authorization across applications.
PentestGPT
An AI-powered autonomous agent for penetration testing and CTF challenges that automates vulnerability discovery and flag capture.
nano-vllm
Nano-vLLM is a lightweight, from-scratch implementation of a vLLM-style inference engine designed for fast offline inference with a highly readable codebase.
easy-dataset
A tool for creating LLM fine-tuning datasets by converting unstructured documents into high-quality structured QA pairs and evaluation sets.
botpress
Botpress is a platform for building AI-powered chatbots and assistants using OpenAI, providing a suite of developer tools for creating custom integrations and plugins.
llmware
A unified framework for building private, local, and secure knowledge-based LLM applications, featuring a model catalog of 300+ models and an integrated RAG pipeline.
oh-my-pi
A high-capability coding agent with deep IDE integration, featuring built-in LSP/DAP support, hashline edits, and a vast tool surface for autonomous software engineering.
unstructured
An open-source library for ingesting and pre-processing unstructured documents like PDFs and Word files into structured formats to optimize data workflows for LLMs.
rowboat
Rowboat is an open-source, local-first AI coworker that builds a long-lived knowledge graph from your emails and meeting notes to provide persistent, compounding context for work tasks.
Memori
Memori is a persistent memory layer for AI agents and LLMs that automatically captures and recalls structured context, user preferences, and agent decisions across sessions.
WrenAI
An open-source generative BI engine that allows AI agents to generate, deploy, and govern trustworthy business intelligence and dashboards from any database.
memvid
Memvid is a single-file, portable memory layer for AI agents that provides persistent long-term memory and fast retrieval without the need for external databases.
agency-agents-zh
A library of 266 specialized AI expert roles with defined identities and workflows, compatible with 18 AI programming tools to transform LLMs into a professional agency team.
edict
A multi-agent collaboration framework that uses an ancient Chinese imperial administrative structure to provide institutional oversight, real-time observability, and strict quality control for AI tasks.
kubesphere
KubeSphere is a distributed operating system for cloud-native application management that simplifies Kubernetes management across multi-cloud, edge, and datacenter environments.
agent-lightning
A trainer for AI agents that enables optimization via Reinforcement Learning and other techniques with minimal code changes, regardless of the agent framework used.
easy-vibe
A comprehensive, multilingual learning map and tutorial series that teaches users how to build full-stack AI applications through AI-assisted "vibe coding."
openfang
An open-source Agent Operating System built in Rust that runs autonomous agents on schedules to perform complex background tasks without constant prompting.
DocsGPT
An open-source AI platform for building private intelligent agents and assistants that provide hallucination-free answers based on ingested private documents and web content.
WeClone
WeClone is an end-to-end solution for creating digital avatars by fine-tuning LLMs on a person's chat history from platforms like Telegram, supporting both text and image data.
parlant
An interaction control harness for customer-facing AI agents that uses dynamic context engineering to ensure consistent, compliant, and brand-aligned behavioral control.
web-llm
A high-performance in-browser LLM inference engine that uses WebGPU to run language models locally without a server.
9router
A smart AI router and token saver that optimizes API costs and prevents downtime by providing automated fallback between subscription, cheap, and free AI models.
Chinese-LLaMA-Alpaca
An open-source project providing Chinese-enhanced LLaMA and Alpaca models through vocabulary expansion and instruction fine-tuning for improved Chinese NLP tasks.
DB-GPT
An open-source agentic AI data assistant that connects to databases and files to autonomously write SQL and code for data analysis and reporting.
SWE-agent
An autonomous AI agent that enables LLMs to fix GitHub issues, find security vulnerabilities, and perform custom coding tasks.
dyad
Dyad is a local, open-source AI app builder that allows users to create applications privately on their own machines using their own API keys.
datasets
A lightweight library for easy one-line loading and efficient pre-processing of diverse AI-ready datasets (text, audio, image, video) from the Hugging Face Hub or local files.
skyvern
Skyvern is an AI-powered browser automation tool that uses Vision LLMs and Playwright to automate web workflows without relying on brittle XPaths or custom scripts.
Anthropic-Cybersecurity-Skills
A comprehensive open-source library of 817 structured cybersecurity skills and workflows designed to give AI agents the domain expertise of a senior security analyst.
mlc-llm
MLC LLM is a universal deployment engine and ML compiler that enables high-performance native execution of large language models across diverse hardware and platforms.
GenAI_Agents
A comprehensive repository of GenAI agent tutorials and implementations, providing a structured path from basic bots to complex multi-agent systems using frameworks like LangGraph and LangChain.
Ford AI Automation Failure: How Replacing Workers Backfired
Ford's attempt to replace human workers with AI-driven automation failed, leading to operational setbacks and public criticism.
DeepSeek-Reasonix
A DeepSeek-native AI coding agent for the terminal that uses a config-driven Go harness to minimize token costs and automate coding tasks.
ai
A provider-agnostic TypeScript toolkit for building AI-powered applications and agents with a unified API for multiple LLM providers and integrated UI hooks.
agenticSeek
AgenticSeek is a private, local AI assistant that autonomously browses the web, writes code, and executes complex tasks while keeping all data on the user's device.
Scrapegraph-ai
A Python library that uses LLMs and graph logic to extract structured data from websites and local documents using natural language prompts.
semantic-kernel
An enterprise-ready orchestration framework and SDK for building, orchestrating, and deploying AI agents and multi-agent systems across multiple LLM providers.
langfuse
An open-source LLM engineering platform for developing, monitoring, and evaluating AI applications through observability, prompt management, and testing datasets.
SillyTavern
SillyTavern is a locally installed user interface that provides a unified frontend for interacting with various LLM APIs, image generation engines, and TTS models.
onyx
Onyx is an open-source AI platform that serves as an application layer for LLMs, providing advanced capabilities like Agentic RAG, deep research, and custom agents in a self-hostable interface.
prompt-optimizer
An AI prompt optimization tool that iteratively improves prompts for text and image generation models to enhance output quality and accuracy.
PageIndex
A vectorless, reasoning-based RAG system that uses hierarchical tree indexing and LLM-driven tree search to provide highly accurate and traceable retrieval for long professional documents.
graphrag
GraphRAG is a data pipeline and transformation suite from Microsoft that uses knowledge graphs to extract structured data from unstructured text, enhancing an LLM's ability to reason over private data.
khoj
Khoj is an open-source personal AI assistant that serves as a second brain, allowing users to chat with their own documents and the internet using various LLMs.
AstrBot
An all-in-one open-source Agent chatbot platform that integrates LLMs with mainstream instant messaging apps to create personal companions or enterprise AI assistants.
Vane
Vane is a privacy-focused, self-hosted AI answering engine that combines web search with local or cloud LLMs to provide cited answers while keeping data private.