Explore the directory

A lightweight Flutter engine embedder for Raspberry Pi and other Linux devices that runs without X11 or Wayland, for booting straight into a Flutter app from the command line.

• Mobile

A community-maintained directory of Retrieval-Augmented Generation frameworks, engines, evaluation tools and resources, with guidance on choosing between a RAG framework you integrate and a RAG engine you run as a standalone platform.

• RAG
• Curated lists

An MCP server for GitLab with 261 granular tools covering projects, merge requests, issues, pipelines, wikis, releases and more, supporting self-hosted GitLab instances, multiple auth modes, and JMESPath filtering to shrink tool results.

• MCP servers
• Git

An open-source vulnerability scanner for LLMs and agent workflows that probes for jailbreaks, fuzzes inputs across text, image and audio, and can run as a CI check to catch regressions in an AI system's safety guardrails.

• Security

An installable Agent Skills package that turns Claude Code, Cursor or Codex into a maintainer of a Karpathy-style LLM wiki: compiling ingested sources into durable, cross-linked markdown pages and answering questions with citations.

• Agent skills
• Documentation tools

An on-device Android AI agent, built natively in Kotlin and Flutter, that operates terminals, manages system tasks such as alarms and calendar events, and can bridge to a Codex CLI session running on a desktop machine.

• Agent frameworks
• Mobile

A MySQL-compatible, cloud-native database that combines transactional, analytical, full-text, and vector search workloads in one engine, with Git-style branching, snapshots, and time travel for data.

• Databases

A guide and reference for the Figma MCP server, which brings Figma design context, components and variables directly into an AI coding agent for generating code from selected frames or converting a web page into a Figma design.

• MCP servers
• Design tools

A curated, use-case-organized list of open source and source-available tools for running and coordinating multiple coding agents, from terminal session managers to autonomous loop runners and multi-agent swarms.

• Coding agents
• Curated lists

An experimental fork of Windows Terminal with native integration for Agent Client Protocol (ACP) coding-agent CLIs such as GitHub Copilot, Claude, Codex and Gemini, alongside all of Windows Terminal's usual tabs, profiles and shortcuts.

• Coding agents
• Terminals

A native, open-source macOS notch app that gives a real-time control surface for AI coding agents across thirteen tools and fifteen-plus terminals and IDEs: session status, permission approvals, and instant jump-back to the right terminal.

• Coding agents
• Desktop utilities

A BYOK desktop AI assistant and universal MCP client that connects almost any LLM provider to MCP servers, with chat, image and video generation, RAG over local files, voice mode and system-wide AI commands.

• MCP servers
• Inference

A Python library for training and evaluating knowledge graph embedding models, with dozens of built-in models and datasets and a high-level pipeline function for benchmarking a model on a dataset in a few lines of code.

• Models

A continuously updated bibliography of papers and practical resources on medical large language models, built from a peer-reviewed survey covering how such models are built, evaluated, deployed clinically and challenged by real-world use.

• Papers

A C-language AI agent framework for ESP32-series IoT devices that defines device behavior through chat and dynamic Lua loading, running the full sense-decide-execute loop locally on a few-dollar chip.

• Agent frameworks

A Swift API for the MLX array framework, letting machine learning research and inference run natively on Apple silicon from Swift, with example apps for chat, text generation and Stable Diffusion image generation.

• Inference
• Libraries

An open-source, self-hostable platform for evaluating, tracing, simulating and guarding LLM and AI agent applications in one feedback loop, with a low-latency Go gateway and OpenTelemetry-native observability.

• AI evals

A local MCP server that gives your own ChatGPT session read, search, edit and review access to repositories you explicitly allow on your machine, with bounded local code-intelligence tools for impact analysis and change review.

• MCP servers
• Code quality

An open-source network boot firmware that extends PXE with HTTP/HTTPS, iSCSI, FCoE and AoE SAN booting, a scripting language, and interactive boot menus and forms.

• Networking

A free, open-source SEO and GEO MCP server and Claude skill set that runs keyword research, rank tracking, audits and AI-visibility analysis against your own Google Search Console, GA4 and Ads data, with DataForSEO built in at no markup.

• MCP servers
• Agent skills

A CVPR 2025 benchmark for evaluating document-parsing systems across 1,651 pages of diverse real-world documents, with detailed block- and span-level annotations and evaluation code.

• RAG
• AI evals

A research-preview, fully on-device real-time multimodal voice assistant with features similar to OpenAI's GPT-Live, using hands-free turn-taking detection and sentence-by-sentence streamed replies, with an optional cloud research step.

• Speech

A Python multi-agent framework that unifies tools, models and agents into modular, hot-swappable Oxy components, with dynamic task decomposition, auditable agent negotiation, and a distributed scheduler for scaling agent systems.

• Agent frameworks

A context and harness engineering system for Claude Code and OpenAI Codex that enforces quality gates, keeps durable project context across sessions and compaction, and turns completion claims into verified evidence.

• Agent skills
• Code quality