Explore the directory

A Laravel package that speaks the Model Context Protocol over both Streamable HTTP and STDIO, exposing a single facade for listing and calling MCP tools and reading resources, used by the LarAgent framework and other Laravel AI packages.

• MCP servers
• Backend

A TypeScript equivalent of mcp-client-langchain-py: a simple command-line client, built on a LangChain ReAct agent, for testing and exploring Model Context Protocol servers, with automatic tool-schema adjustments for broader LLM compatibility.

• MCP servers

A simple text-based Python CLI, built on LangChain's ReAct agent, for testing and exploring Model Context Protocol servers from the command line, configured through a JSON5 file listing servers and their LLM provider.

• MCP servers

A stateless daemon that turns a labeled GitHub issue into a pull request using headless Claude Code, asking clarifying questions on vague issues, running an architect-versus-product-owner debate before implementing, and parking failures instead of retrying unattended.

• Coding agents
• Git

A fast, embedded semantic vector database written in C/C++ that stores vectors and text metadata as memory-mapped flat files, with HNSW approximate nearest-neighbor search, timestamp-range filtering, and adapters for LangChain, LlamaIndex and Claude Code via MCP.

• Agent memory
• Databases

A command-line wrapper around llama.cpp's llama-server that gives it an Ollama-like workflow: starting and stopping a background server, downloading and inspecting GGUF models interactively, and automatically applying a model's recommended sampling parameters.

• Inference
• CLI tools

A Go command-line tool that compiles a folder of PDFs, Markdown and text files into a self-contained GraphRAG agent packaged as a single Docker container, with an embedded vector store, graph database and keyword index instead of a hosted service stack.

• RAG
• CLI tools

A native macOS app for running open large language models entirely offline through Apple's MLX framework, with a llama.cpp/GGUF fallback engine, vision and audio input, image generation, thinking-mode visibility, and speculative decoding for faster output.

• Inference
• Desktop

An on-device AI backend library for building in-game assistance features - screenshot understanding, retrieval-augmented Q&A, memory and speech recognition - accelerated on Intel GPU and NPU hardware, exposed to a game client over a local HTTP API.

• RAG
• Libraries

A Postgres-backed vector memory layer for AI agents, using a local BERT model for embedding search with no LLM calls in the hot path, distributed as a plugin for the hermes-agent framework and as a standalone MCP server.

• Agent memory
• Databases

A lightweight, strictly typed Python framework for building LLM agents and structured workflows, usable either embedded as an application's orchestration layer or standalone with cross-session memory, skills and a terminal UI.

• Agent frameworks

A structurally enforced software-development pipeline in which agent teams turn a GitHub issue or rough description into a reviewed pull request, with peer review, context tracking and a zero-credential sandbox designed to keep every merge decision with a human.

• Coding agents
• Agent frameworks

An experimental iOS app that runs DeepSeek Harness, a coding-agent CLI, entirely on an iPad or iPhone by embedding the iSH-ARM64 Linux emulator, booting Alpine Linux with Node.js, and showing the harness's own web UI in an in-app browser view.

• Coding agents
• Mobile

A self-hosted retrieval-augmented generation framework for teams that cannot send data to third-party APIs, with role-based access control, support for several LLM providers, and natural-language questions answered over uploaded tables via generated SQL.

• RAG
• Databases

An MCP server that gives AI assistants natural-language, read-only access to semantic 3D city models stored in a 3DCityDB v5 PostGIS database, dynamically resolving CityGML classes and properties so no manual prompt engineering is needed.

• MCP servers
• Databases

A decoding method and reference implementation that speeds up LLM inference by computing geometric upper bounds on token logits to skip most of the output vocabulary at each decoding step, without retraining the model.

• Inference

An open-source governance layer that intercepts AI agent tool calls and checks them against African financial and data-protection regulations before they execute, with adapters for LangChain, LangGraph, CrewAI and AutoGen.

• AI evals
• Security

A research framework for auditing collusion between cooperative, tool-calling LLM agents, built on the Terrarium multi-agent environment, that identifies a taxonomy of collusion types across different models, network topologies and environments.

• AI evals

An open-source platform for goal-driven AI agents that plan, run and measure work on a schedule against a metric you set, running on coding-agent CLIs such as Claude Code, Codex, Cursor and Pi that a developer already uses.

• Agent frameworks
• Workflow automation

A training and serving stack for fine-tuning open code models such as StarCoder2 and DeepSeek-Coder into low-latency IDE completion models, aimed at low-resource languages and on-premises deployment that mainstream hosted copilots skip.

• Models

A from-scratch, hand-built decoder-only transformer training project, currently a 152-million-parameter model pretrained on about 15 billion tokens with RoPE, RMSNorm and SwiGLU, released as a Hugging Face-compatible checkpoint with a live demo.

• Models
• Tutorials

A curated list mapping the tools, libraries and patterns for reducing the cost of running large language models in production, covering observability, routing, caching, prompt compression, quantization and provider pricing data.

• Curated lists

A community-maintained directory of third-party integrations built on OpenAI's Apps SDK, an MCP-based protocol that lets developers extend ChatGPT with real-time tools and data, organized by category with descriptions and use cases.

• MCP servers
• Curated lists

A curated, YAML-driven list of AI tools grouped into chatbots, code assistants, developer tools, search engines, text-to-image and local-inference categories, with entries mostly drawn from the Chinese AI tooling ecosystem.

• Curated lists