Explore the directory

A PyTorch implementation of BitNet, a 1-bit Transformer architecture that replaces standard linear layers with a quantized BitLinear layer to scale large language models with lower-precision weights.

• Models

A self-hosted, always-on personal AI that indexes email, meetings, GitHub, Linear and Slack into a memory graph, then runs tasks through voice, a scratchpad, chat or messaging apps, spinning up coding-agent sessions when needed.

• Agent frameworks
• Agent memory

An open-source desktop AI assistant for Linux, Windows and macOS that connects to many model providers and adds agents, RAG, vision, image and video generation, computer use and voice in one chat-style interface.

• Inference
• Generative media

An open-source control plane for AI and agent traffic, built on Envoy, that gives one OpenAI-compatible API across hosted model providers, self-hosted inference and MCP servers while centralizing credentials, routing, quotas and failover.

• LLM gateways

An open-source AI agent for automated, autonomous penetration testing from the terminal, using a developer's own Claude, GPT or other LLM subscription across 13+ specialized agents and OWASP-based test cases.

• Security

A knowledge compiler that turns raw sources such as papers, notes, READMEs, transcripts and web pages into an interlinked, citation-traceable Markdown wiki that agents and people can browse, query, lint and export.

• Agent memory
• Documentation tools

A Java metaprogramming library that parses source files into a full AST and provides an API for analyzing, rewriting, transforming and transpiling Java source code, supporting Java versions up to 25.

• Code quality

A C/C++ speech-to-text inference library that runs 16 model families and more than 60 model variants on the ggml runtime, with Metal, Vulkan and CUDA GPU backends plus an accelerated CPU path.

• Speech

An open-source agent that uses Ghidra and LLMs such as Claude, Codex or OpenAI-compatible models to reconstruct and validate C/C++ functions from compiled binaries.

• Debugging

A self-hosted memory backend that gives AI agent pipelines such as LangGraph, CrewAI, AutoGen and Claude a shared, persistent memory with a causal knowledge graph, reachable over a REST API or MCP.

• Agent memory

A Java API for compile-time or runtime code generation targeting Android's Dalvik VM, most commonly used to let the Mockito mocking library create class proxies in Android instrumentation tests.

• Testing

A Python trading framework that runs AI agents or hand-written rule-based strategies through the same backtest-then-broker lifecycle, across twelve broker integrations covering stocks, options, futures, forex, crypto and prediction markets.

• Agent frameworks
• Libraries

A cross-platform, high-performance C++17 GPU UI framework with GLFW/SDL2 window backends and OpenGL/Vulkan rendering, for building native application interfaces.

• Desktop

A local retrieval-augmented generation app that answers questions about your own PDFs, Word files and text using Ollama, citing the file and page each answer came from.

• RAG

An MCP server that turns a large codebase into a searchable, hierarchical feature graph, combining retrieval, AST parsing and clustering so agents can navigate and edit code by meaning rather than exact text.

• MCP servers
• Agent memory

A fast Android decompiler front end that queries a compiled APK directly as a database instead of building a large index, aiming to search and decompile code in milliseconds rather than minutes.

• Debugging

A research method and PyTorch implementation for fine-tuning text-to-image diffusion models on a handful of example images to add a new concept, without retraining the whole model.

• Models
• Generative media

A curated, categorized index of frameworks, templates and community projects built around LangChain and LangGraph, covering building, observing, evaluating and deploying LLM agents.

• Agent frameworks
• Curated lists

A local memory service that gives AI coding agents such as Claude Code, Codex and OpenClaw a shared, persistent memory so they keep context across sessions instead of starting over.

• Agent memory

A collection of command-line tools, skills, agents, hooks and plugins that add productivity features to Claude Code, Codex CLI and similar terminal-based coding agents.

• Agent skills

A conservative maintenance bot for GitHub repositories that reviews open issues and pull requests on a schedule, posts durable review reports, and turns narrow, trusted findings into guarded automerge or repair work.

• Git

A Windows and macOS desktop app that sends one question to more than a dozen AI chatbots at once, including ChatGPT, Gemini, Claude and Copilot, and shows their answers side by side.

• Inference

A framework and hosted API for building AI agents that operate on websites, combining scripted automation with AI so routine steps run as code and models are used only where judgment is needed.

• Browser automation

A Ruby framework for building LLM-powered applications, providing a unified interface across providers such as Anthropic, AWS Bedrock, Google Gemini and OpenAI for embeddings, prompt completions, chat and retrieval-augmented generation.

• Agent frameworks
• RAG