Explore the directory

A 100-day self-study challenge that links one AI or machine-learning concept per day to a companion blog post, moving from machine-learning foundations through neural-network training to AI agents in production.

• Tutorials

An example iOS Xcode project showing how to run the YOLOv5 object-detection model, converted to Core ML, on a photo picked from the device's photo library.

• Mobile
• Tutorials

A free, open-source AI and machine-learning curriculum of more than 950 hands-on Jupyter notebooks, covering Python, deep learning, large language models, retrieval-augmented generation, agents, prompt engineering, fine-tuning and MLOps.

• Tutorials

A Python automation layer for authoring and filling HWPX documents, Hancom Office's format, providing a Python API, a command-line tool and an optional MCP server for AI agents, without requiring Hancom Office or Windows.

• Libraries

An MCP server that bridges multiple AI coding CLIs, such as Claude Code, Antigravity, Codex and OpenCode, so any one of them can call the others as tools and get a second opinion.

• Coding agents
• MCP servers

Inference and embedding code for LucaOne, a foundation model for nucleic-acid and protein sequences, with Hugging Face support for fine-tuning on sequence- and residue-level biological tasks.

• Models

A pure-Rust, CPU-only library and command-line tool for running LiquidAI's LFM2.5-8B-A1B language model locally, without a GPU.

• Inference

An interactive platform for learning AI and machine learning through animated visualizations and runnable browser-based Python, paired with more than twenty end-to-end example projects from classical machine learning to production LLM systems.

• Tutorials

A Dart code-generation and build system, used as an alternative to the standard Dart build tools, aimed at faster incremental builds and a simpler configuration model.

• CLI tools
• Libraries

A command-line tool that runs SAST scans or reads existing scan reports from tools such as Checkmarx, CodeQL, Fortify or Snyk, then produces automatic code fixes for the vulnerabilities it can remediate.

• Code quality
• Security

A lightweight Neovim plugin that embeds the Editor Code Assistant, an AI coding assistant, directly into the editor as a chat panel you can trigger with a command or keymap.

• Coding agents
• Editors

A voice-first AI agent that combines a local rule-based decision layer for routine tasks with cloud language models, three tiers of memory, and integrations across several model providers including Chinese-language ones.

• Agent frameworks

A React UI widget that adds Vectara-powered semantic search to a React application with a few lines of code, including a search input, results modal and configurable behavior.

• RAG
• UI kits

A binary analysis and decompilation engine built on LLVM that lifts native and smart-contract code to one-to-one instruction-level semantics, for use by command-line tools, other programs and AI agents through a single C API.

• Debugging

A CUDA technique for large language models that batches many independent structured-output decisions into one parallel pass over a shared prompt, instead of generating each field as separate constrained JSON.

• Inference

An open-source AI agent platform that unifies a multi-provider LLM gateway, a bilingual command-line interface, a browser-based web interface and an extension system into one assistant for Windows, macOS and Linux.

• Agent frameworks
• LLM gateways

A from-scratch pure C inference engine that runs GLM-5.2, a 744-billion-parameter mixture-of-experts model, on a single machine with about 16 GB of RAM by quantizing to int4 and streaming inactive experts from disk.

• Inference

A knowledge-graph tool for AI code review that offers semantic search and call-graph resolution across a codebase, aimed at making reviews more token-efficient.

• Agent memory
• Code quality

A local, self-hosted multi-agent orchestrator that runs already-installed CLI coding agents such as Codex, Claude Code, Gemini and OpenCode as one operator-led team, with a live web dashboard.

• Coding agents

A frequently updated list of open source AI agent frameworks and related tools, tracking each project's category, license, programming language and issue-tracker activity.

• Agent frameworks
• Curated lists

An open-source AI assistant for exploring the MITRE ATLAS knowledge base of adversarial machine-learning tactics, techniques and mitigations, through natural-language questions, an MCP server, or direct customization.

• Security

A collection of open-source example applications showing how to build on-device AI apps with full NPU acceleration using ZETIC's Melange model-conversion platform, covering offline translation, voice and vision tasks.

• Mobile
• Tutorials

A Python SDK for building vector search, retrieval-augmented generation and AI applications directly on Oracle AI Database, combining semantic similarity with relational and spatial filtering.

• RAG
• Databases

A containerized terminal development environment bundling modern CLI and TUI tools, several AI coding assistants, language SDKs and shell aliases, runnable the same way on a desktop, VPS or cloud workspace.

• Terminals
• Containers