Explore the directory

A self-hosted zero-trust access gateway that shares local language models, databases and internal services over authenticated APIs and browser-based terminals, without opening inbound ports on the private network.

• Auth
• Networking

An MCP server that connects an AI assistant to a Chrome extension running on the user's own browser profile, so it can navigate, click and read pages while keeping existing logins and avoiding bot-detection friction.

• MCP servers
• Browser automation

A serving build and set of patches that run a large mixture-of-experts language model across two consumer GPUs and system memory, offloading inactive experts to RAM to fit a 256,000-token context.

• Inference

A local Windows proxy that imitates the Ollama API so Visual Studio Copilot Chat's bring-your-own-model feature can be pointed at OpenAI, Anthropic or Ollama-compatible providers instead.

• LLM gateways

An open-source framework for testing and observing multi-agent delegation, tool execution, MCP workflows and permissions, with policy checks, replayable runs and diagrams of who delegated what to whom.

• AI evals
• Testing

An ABAP implementation of the Model Context Protocol server side, letting an SAP system expose prompts, resources and tools to an MCP client without server-sent-event features such as notifications.

• MCP servers

An IntelliJ plugin that adds ghost-text code completion backed by a language model, using the Hugging Face Inference API or any compatible HTTP endpoint, with the prompt automatically sized to the model's context window.

• Editors

A multi-agent framework in which a planner, paired coder-and-reviewer teams, a coordinator and a memory-extracting agent divide up a complex task, work in parallel, and build a searchable knowledge base from what they learn.

• Agent frameworks
• Agent memory

A Claude Code skill that teaches the assistant to author deterministic multi-agent orchestration scripts for Claude Code's unreleased Workflow tool, where ordinary JavaScript control flow drives fresh-context agent calls.

• Agent frameworks
• Agent skills

An annotated, actively updated reading list of over 500 papers on LLM agents, organized by function such as planning, memory, tool use and safety, built as a companion to a survey paper.

• Curated lists
• Papers

A command-line tool that stores a repository's tasks and architecture decisions in a project-local folder, so a coding agent can see what was decided and why, and claim, verify and hand back work.

• Agent memory
• CLI tools

A vendor-neutral collection of skill files that teach an AI coding agent how to instrument code with OpenTelemetry, covering SDK setup, semantic conventions, collector pipelines and OTTL transformations.

• Agent skills
• Monitoring

A provider library that lets a developer run Qiskit quantum programs on quantum devices and simulators available through Amazon Braket.

• Libraries

An MLX implementation of Google's TurboQuant method that compresses both model weights and the key-value cache of large language models on Apple Silicon, letting bigger models fit in less memory.

• Models
• Inference

A lightweight Java library that adds AI agent workflow orchestration to an existing Java web application, running on Java 8 or newer with a range of built-in node types.

• Agent frameworks

Research code for teaching a multimodal language model to recognize and remember user-specific concepts through retrieval augmentation, so it can discuss a person's own subjects in later conversations.

• RAG
• Papers

A self-hosted platform for running a team of named AI agents with their own roles, models and memory, where one agent can break a goal into tasks and delegate them to the rest of the team.

• Agent frameworks

A collection of reference notes and sample code covering LLM fundamentals, retrieval-augmented generation, fine-tuning and agent frameworks, with runnable examples in LangChain, AWS Strands Agents and Google's Agent Development Kit.

• Tutorials

A tree-sitter-based compiler that parses an entire codebase into a queryable map of symbols, call edges and class relationships, so a coding agent can look up structure directly instead of reading whole files.

• Agent memory

A curated, multi-language guide to open-source alternatives across the AI developer stack, from coding agents and local inference to vector databases, evaluation and observability.

• Curated lists

A local, portable evidence ledger for research and engineering work done with an AI model, tracking claims, sources and open gaps across sessions and models so an answer can be checked rather than taken on faith.

• AI evals

A TypeScript walkthrough demo showing how to build semantic search over a CSV dataset using the Pinecone vector database and a sentence-transformers embedding model.

• Databases
• Tutorials

A reference implementation for building a retrieval-augmented-generation chatbot and document management system, with a FastAPI backend, a document extraction pipeline and a choice of language model providers.

• RAG
• Backend

A dependency-free C inference engine that runs Qwen3-TTS text-to-speech models on the CPU using only a BLAS library, with support for nine voices and ten languages.

• Inference
• Speech