An open-source observability platform that stores telemetry data in S3 and uses AI agents and natural language queries to detect anomalies and explore logs, metrics, and traces.

A desktop application for managing multiple OpenAI Codex accounts, allowing users to easily switch between them and monitor usage quotas.

A desktop app for running multiple AI coding agents in parallel, using Git worktrees to isolate tasks and integrate with project management tools.

Lemonade is an open‑source local AI server that runs LLMs, speech, TTS, image and other multimodal models on your own CPU/GPU/NPU. It provides a standard OpenAI‑compatible HTTP API, a CLI for model management, and two distribution flavors – a full server service and a portable embeddable binary. Supports Windows, macOS, Linux (many distros, Docker, Snap) and a broad set of hardware back‑ends (CUDA, ROCm, Vulkan, Metal, AMD NPU, etc.).

A self-hosted terminal server that provides AI agents and automation tools a sandboxed or bare-metal environment to execute code and manage files via a REST API.

Warren is an open‑source, self‑hosted platform that turns LLM‑based coding agents into managed, observable workloads. It provides isolated workspaces, lifecycle control, spend limits, live event streams, automatic Git commits (and PRs), and supports local, Docker, or Kubernetes runtimes. Ideal for individuals or small teams that want to run coding agents securely on their own infrastructure.

An OpenAI API-compatible inference proxy that implements 20+ optimization techniques to improve LLM reasoning accuracy without requiring model training.

A workflow orchestration framework for building resilient, automated data pipelines in Python with built-in scheduling, monitoring, and error recovery.

A native ARM64 runtime for Mario Kart Wii and the Retro Rewind mod, using static recompilation to run the game on Android and Apple platforms via Metal and Vulkan.

A bridge that connects AI agents to Cheat Engine via the Model Context Protocol, enabling natural language interaction with program memory for reverse engineering and modding.

A native macOS application for managing Apple's container tooling, featuring specialized support for local AI model sandboxing and Kubernetes clusters.

An autonomous multi-agent system for 24/7 vulnerability discovery that uses LLMs to orchestrate security tools and filters results through an AI reviewer for human approval.

A Vulkan-based frame generation and spatial scaling tool for SteamOS and Linux gaming that integrates with Lossless Scaling models to improve FPS and visual quality.

A library for post-training foundation models using techniques like SFT, DPO, and GRPO to align them with human preferences and specific tasks.

An open-source data engineering agent that automates SQL authoring, semantic modeling, and pipeline generation by connecting warehouses, catalogs, and BI tools.

A collection of Nix packages for AI coding agents and development tools, providing daily updated, easy-to-install versions of popular AI assistants.

An AI-powered database client and SQL workspace that allows users to generate, explain, and optimize SQL queries using natural language across 40+ supported databases.

A multimodal data layer and visual debugger for physical AI, allowing developers to log, query, and visualize multi-rate sensor data in real-time.

A method pack that enforces engineering discipline on AI coding agents to reduce reworks and ensure changes are verified with evidence.

A scikit-learn compatible tabular foundation model that enables zero-shot classification and regression on mixed-type tabular datasets using in-context learning.

A shared project memory system for engineers and AI agents that stores architecture, decisions, and handoffs in Git as structured Markdown and code-linked explanations.

A high-performance Python library for extracting and manipulating PDF and Office documents, featuring specialized tools for converting documents into LLM-ready Markdown for RAG pipelines.

A methodology and set of patterns for structuring AI agent workflows using a filesystem hierarchy instead of complex orchestration frameworks, enabling human-in-the-loop review and high observability.

An API skill package that enables AI coding tools to interact with EasyEDA Pro for automated debugging and extension development.

A CLI and MCP server that bundles project files with prompts to provide grounded AI reviews and audits via APIs or browser automation.

ZLUDA is a drop-in replacement for CUDA that enables unmodified CUDA applications to run on non-NVIDIA GPUs with near-native performance.

An open-source governance layer for AI agents that uses deterministic scheduling and policy-as-code to ensure agent runs are isolated, reproducible, and verifiable via signed audit receipts.

Attention Span provides three markdown‑based output‑style plug‑ins (Attention‑kind, Spartan, Rundown) for Claude Code and other LLM agents. The styles keep the model’s reasoning unchanged but make replies up to ~43 % shorter and easier to skim, helping users with limited attention and reducing token spend. Install via a one‑step Claude Code plugin or manually drop the markdown files, then activate with `/style` or skill commands. Works with other agents after stripping front‑matter. Complementary tools (Token Optimizer, Outsourcerer) address deeper token waste.

AutoGluon is an automated machine learning (AutoML) library that finds the best combination of models for tabular, time series, and multimodal data to achieve high predictive performance with minimal code.

A 3D virtual office for AI agents that turns background automation into a visible, immersive workspace for real-time monitoring and collaboration.

A comprehensive benchmarking tool for generative AI models that measures latency and throughput across various inference engines and multimodal APIs.

A visual workspace for collaborating with coding agents, featuring WYSIWYG editors, parallel session management via git worktrees, and a mobile companion app for diff reviews.

A CLI and MCP server that provides programmatic access to Gemini Notebook (NotebookLM), enabling AI agents and scripts to manage notebooks, sources, and generate studio content.

A Rust-based MCP server and CLI that allows AI agents to control a Linux desktop, supporting Wayland and X11 across multiple desktop environments.

A mobile and macOS application for running open-source LLMs locally on-device, providing a private and offline environment to experience and evaluate generative AI.

A node-based terminal manager that organizes terminals and AI agents on an infinite spatial canvas, featuring persistent sessions and a built-in kanban board.

A high-performance in-browser LLM inference engine that uses WebGPU to run language models locally without server-side processing.

A concise domain-specific language and compiler built on TVM for developing high-performance GPU and CPU kernels like GEMM and FlashAttention across multiple hardware backends.

An AI-native API gateway based on Istio and Envoy that provides unified management, observability, and hosting for LLM APIs and MCP servers.

A token-efficient MCP server that allows AI agents to interact with the Cloudflare API using server-side code execution to avoid context window exhaustion.

An open-source, self-hosted identity and access management platform providing single sign-on (SSO) and multi-protocol authentication for applications.

A protocol translation gateway that turns Windsurf/Devin's internal AI model access into standard OpenAI, Anthropic, and Gemini compatible APIs.

A lightweight all-in-one terminal supporting 30+ protocols including SSH, RDP, and databases, featuring an autonomous AI agent that plans and executes shell commands.

An AI-powered code review platform that integrates with Git providers to automate PR reviews, enforce custom team rules, and track technical debt.

A CLI and skill set that enables developers and AI coding assistants to build, evaluate, and deploy enterprise-grade agents on the Gemini Enterprise Agent Platform.

An open-source, self-hosted algorithmic trading platform that provides a unified API for 36 brokers and tools for Python-based, no-code, and AI-assisted trading.

A TypeScript SDK for the Model Context Protocol (MCP), enabling developers to build standardized servers and clients that provide context, tools, and resources to LLMs.

A scalable reinforcement learning framework for LLM agents that enables training across diverse agent types and sandboxes with token-level trajectory recording.