open-code-review: OpenCodeReview – AI‑powered, line‑accurate code review for any Git repo
OpenCodeReview is an open‑source CLI that runs AI‑driven code reviews on Git diffs or whole files. It combines deterministic file‑selection logic with a configurable LLM (Anthropic, OpenAI, or custom) to produce precise, line‑level comments. Install via npm or pre‑built binaries, configure a provider, then run `ocr review` (or `ocr scan`) to get automated reviews that are cheaper and more accurate than generic code‑review agents.
texar: a modular toolkit for NLP and text generation with support for multiple learning paradigms
Texar is a modular toolkit for NLP and text generation that provides easy-to-use ML modules and pre-trained models for fast prototyping and experimentation.
LMOps: a research suite for optimizing LLM prompt intelligence, inference acceleration, and in-context learning
A research initiative focused on fundamental technologies to improve LLM prompting, inference speed, and context handling for building AI products.
MoneyPrinterTurbo: a one-stop AI short-video generator that automates scripting, asset matching, and publishing
An AI-powered short-video generation tool that automatically creates scripts, matches stock footage, and adds voiceovers and subtitles from a simple topic.
ai-agent-book: a comprehensive engineering guide and code library for designing and implementing production-grade AI agents
A comprehensive open-source companion to a book on AI Agents, providing theoretical guides and practical code implementations for context engineering, RAG, tool-use, and multi-agent systems.
fiftyone: a visual AI development tool for dataset curation and model evaluation
An open-source tool for building high-quality computer vision datasets and models through visualization, labeling, and evaluation.
obsidian-mind: a persistent memory vault for AI coding agents to track professional context and performance evidence
An Obsidian vault template that gives AI coding agents persistent memory, allowing them to track projects, decisions, and performance evidence across sessions.
json_repair: a Python library to repair malformed JSON from LLMs and APIs using heuristics and schema guidance
A Python library that repairs malformed JSON from LLMs and APIs by fixing syntax errors and providing schema-guided recovery.
khazix-skills: a collection of standardized instruction sets to extend AI agent capabilities for system utility, research, and writing
A collection of standardized AI agent skills for tasks like disk cleanup, AI news tracking, project documentation synchronization, and deep research reports.
DeepSpeed: a system optimization library for training trillion-parameter deep learning models at extreme scale
A deep learning optimization library that enables the training of models with trillions of parameters by optimizing memory and compute efficiency across distributed systems.
agent-governance-toolkit: a deterministic policy enforcement and governance toolkit for autonomous AI agents
A governance framework for autonomous AI agents that provides deterministic policy enforcement, identity management, and audit logging to prevent unauthorized actions.
OmniRoute: a free AI gateway that aggregates 268 providers with automatic fallback routing and token compression
An AI gateway that aggregates hundreds of AI providers and free tiers into a single endpoint, featuring automatic fallback routing and token compression to eliminate rate limits and reduce costs.
mission-control: a self-hosted control plane for dispatching tasks and governing multiple AI agent runtimes
A self-hosted control plane for operating AI agents, providing a centralized dashboard to dispatch tasks, track spend, and coordinate multiple agent runtimes.
OpenCLI: a framework to turn websites and Electron apps into deterministic CLI interfaces for humans and AI agents
A tool that converts websites and browser sessions into command-line interfaces, enabling humans and AI agents to automate web interactions using logged-in Chrome sessions.
TencentDB-Agent-Memory: a layered memory system that uses symbolic Mermaid graphs and semantic pyramids to optimize agent context and token usage
A layered memory system for AI agents that uses symbolic representations and hierarchical storage to reduce token usage and improve long-term context retention.
AI-Novel-Writing-Assistant: a director-style AI production system for managing the full lifecycle of long-form novel writing
An AI-native production engine for long-form novels that uses a director-style workflow to manage planning, character consistency, and world-building from a single inspiration.
ruoyi-ai: an enterprise-grade full-stack AI platform with multi-agent orchestration and visual workflow design
An enterprise-grade full-stack AI platform providing multi-agent orchestration, RAG, and visual workflow design for building AI assistants.
portaljs: an AI-native framework for building data portals with agentic architecture advisory and Next.js scaffolding
An AI-native framework for building data portals that uses agentic skills to recommend infrastructure and scaffold Next.js frontends with pluggable data backends.
JustHireMe: a local-first AI job intelligence workbench for scraping, ranking, and tailoring application materials
A local-first AI job intelligence workbench that scrapes job leads, ranks them by fit using GraphRAG and vector search, and generates tailored application materials.
Observal: a control plane and system of record for managing and distributing internal AI agents and components
A control plane and system of record for internal AI components that provides a centralized registry for discovery, distribution, and usage insights for AI agents and MCP servers.
OpenKB: a vectorless knowledge base system that compiles documents into a structured wiki for compounding AI knowledge
An open-source system that compiles raw documents into a structured, interlinked wiki-style knowledge base using LLMs and vectorless, reasoning-based retrieval.
langgraphjs: a low-level orchestration framework for building controllable stateful agents with durable execution and human-in-the-loop oversight
A low-level orchestration framework for building controllable, stateful AI agents with support for durable execution, long-term memory, and human-in-the-loop oversight.
embabel-agent: a JVM agent framework that uses dynamic AI planning to mix LLM interactions with strongly typed code
A JVM-based framework for authoring agentic flows that combines LLM interactions with strongly typed domain models and dynamic AI planning.
optillm: an OpenAI-compatible inference proxy that boosts LLM reasoning accuracy via inference-time optimization techniques
An OpenAI API-compatible inference proxy that implements 20+ optimization techniques to improve LLM reasoning accuracy without requiring model training.
jupyter-ai: an open source extension that connects AI agents to computational notebooks in JupyterLab
An open source extension for JupyterLab that connects AI agents to computational notebooks, allowing them to read/write files and run terminal commands.
terax-ai: a lightweight terminal-first AI-native dev workspace with agentic workflows and local model support
A lightweight, terminal-first AI-native development workspace that integrates a GPU-accelerated terminal, code editor, and agentic AI capabilities.
awesome-llm-apps: what it is, what problem it solves & why it's gaining traction
A comprehensive cookbook of 100+ ready-to-run AI agent and RAG templates that developers can clone and customize to ship production LLM apps.
mlflow: an open-source AI engineering platform for the full lifecycle management of agents, LLMs, and ML models
An open-source AI engineering platform that provides tools for debugging, evaluating, monitoring, and optimizing LLM agents and machine learning models.
agno: a framework and runtime for building and managing production-ready agent platforms
Agno is a framework and runtime for building and managing agent platforms, providing an SDK, a runtime engine, and a management UI to maintain full control over the agent stack.
agi: what it is, what problem it solves & why it's gaining traction
A decentralized P2P network where autonomous AI agents collaboratively conduct ML research, pool compute for distributed training and inference, and share discoveries via a global leaderboard.
open-knowledge: a WYSIWYG markdown editor for knowledge bases with integrated AI agent editing and MCP support
A private, local WYSIWYG markdown editor designed for LLM wikis and knowledge bases with integrated AI agent editing and MCP support.
forgecode: an AI-enhanced terminal development environment with specialized agents and ZSH integration
An AI-enhanced terminal development environment that integrates coding agents directly into the shell via a TUI, CLI, or ZSH plugin.
open-swe: an open-source framework for building internal coding agents with isolated cloud sandboxes and multi-channel invocation
An open-source framework for building internal coding agents that integrate with Slack, Linear, and GitHub to automate software engineering tasks in isolated cloud sandboxes.
GenieX: an on-device inference runtime for running LLMs and VLMs locally on Qualcomm Snapdragon hardware
An on-device Gen AI inference runtime for Qualcomm Snapdragon devices that allows users to run LLMs and VLMs locally using GGUF models or optimized Qualcomm AI Hub bundles.
ramalama: a container-centric tool for simplified local AI model serving and hardware-accelerated inference
A tool that simplifies local AI model inference by packaging models and their environments into OCI containers, automating GPU acceleration and host configuration.
code-review-graph: a structural codebase mapper that reduces AI token usage by providing precise blast-radius context for code reviews
A tool that builds a structural graph of a codebase using Tree-sitter and MCP to provide AI assistants with precise, minimal context for code reviews, significantly reducing token waste.
airllm: a memory-efficient inference engine that runs massive LLMs on low-end GPUs by loading one layer at a time
A library that enables running massive LLMs (up to 671B parameters) on consumer GPUs with as little as 4GB-12GB VRAM by loading models layer-by-layer.
heretic: an automatic censorship removal tool that uses optimized directional ablation to decensor language models
A tool for fully automatic censorship removal from language models using optimized directional ablation to suppress refusals while preserving model intelligence.
composio: a tool-integration platform providing 1,000+ pre-authenticated toolkits and session management for AI agents
A tool-integration platform that provides AI agents with over 1,000 pre-authenticated toolkits and session management to turn intent into action.
litellm: a unified AI gateway and SDK to call 100+ LLMs using a single OpenAI-compatible format
An open-source AI Gateway and Python SDK that provides a unified OpenAI-compatible interface for calling 100+ different LLM providers.
TrendRadar: an AI-powered news aggregator and trend analyzer that filters noise and pushes personalized insights to multiple channels
A lightweight trend monitoring assistant that aggregates news from trending lists and RSS feeds, using AI to filter, analyze, and push personalized updates to various platforms.
mem0: an intelligent memory layer for personalized AI agents with hybrid retrieval and temporal reasoning
Mem0 is a memory layer for AI agents and assistants that enables personalized interactions by storing and retrieving user preferences and history over time.
prompts.chat: the world's largest open-source prompt library for AI chat models
An open-source library of curated prompts for AI chat models, featuring a web interface, self-hosting options, and prompt engineering educational resources.
anything-llm: an all-in-one private AI application for chatting with documents and orchestrating AI agents
AnythingLLM is an all-in-one AI application that allows users to build a private ChatGPT-like interface to chat with their documents and automate workflows using AI agents.
council-of-high-intelligence: a structured multi-perspective deliberation framework for high-stakes decision making
A structured multi-perspective deliberation framework that uses diverse AI personas to challenge assumptions and reach high-stakes decisions through adversarial reasoning.
LightLLM: LightLLM – A lightweight, high‑speed Python framework for LLM inference and serving
LightLLM is a Python‑based, high‑performance inference and serving framework for large language models. It combines fast kernels (FlashAttention, Triton) with lightweight, token‑level KV‑cache management, supports multi‑GPU scaling, and adds research‑grade features like constrained decoding and SLA‑aware request scheduling.
read-frog: Read Frog – AI‑enhanced language‑learning extension for browsers
Read Frog is an open‑source browser extension that adds AI‑powered translation, explanations, TTS, subtitle translation, flashcard creation and custom AI actions to any web page. It works on Chrome, Edge and Firefox, supports 20+ LLM providers, batches requests to save cost, and includes a spaced‑repetition system for vocabulary study.
tickflow-stock-panel: a self-hosted A-share quantitative workbench for stock screening, monitoring, and backtesting
A self-hosted quantitative trading workbench for A-share stocks featuring high-speed stock screening, strategy backtesting, and real-time monitoring.
T3MP3ST: a multi-agent offensive-security framework that turns AI coding agents into automated zero-day hunters
A multi-agent offensive-security framework that turns AI coding agents into automated zero-day hunters for web apps, source code, and embedded systems.
yao-meta-skill: a governed lifecycle system for modeling, compiling, and evaluating reusable AI agent skills
A governance and engineering system that transforms raw workflows into reusable, portable, and evaluated AI agent skills across multiple platforms.