A self-hosted AI gateway that centralizes the management of multiple AI model providers, providing a consistent API, routing, and usage tracking for teams and applications.

A unified API gateway providing direct, proxy-free access to multiple frontier LLMs like GPT, DeepSeek, and Claude using a standardized OpenAI protocol.

An end-to-end open source platform for machine learning that provides a flexible ecosystem of tools and libraries for building and deploying ML-powered applications.

A hardware-aware tool that detects your system specs and recommends the best-fitting open-source LLMs based on memory, speed, and quantization.

An autonomous agentic AI system that monitors Git commits for vulnerabilities and manages Jira tickets to ensure continuous compliance with the EU Cyber Resilience Act.

A verification layer for AI coding agents that runs an internal SDK in web apps to prove code changes work by monitoring network, state, and console events.

An open-source Office SDK for embedding customizable spreadsheets, documents, and presentations into applications, featuring a headless runtime for AI agents and automation.

A browser designed for AI agents and humans to work in parallel using isolated workspaces, allowing agents to automate web tasks without interrupting the user's browsing session.

A high-performance, secure sandbox service for AI agents that provides hardware-isolated MicroVMs with sub-60ms startup times and E2B SDK compatibility.

A next-generation AI memory management system that emulates human-like cognitive processes to provide agents with dynamic, evolving long-term memory.

A toolkit to extract and normalize local chat history from multiple AI coding assistants into JSONL format for backup, analytics, or fine-tuning.

A visual registration and configuration tool for Cloudflare WARP / MASQUE that simplifies account setup and generates compatible configurations for multiple proxy clients.

An MCP server that provides AI coding agents with IDE-level semantic code retrieval, refactoring, and debugging tools to improve reliability in complex codebases.

A lightweight agentic RL framework that allows developers to train AI agents using reinforcement learning with zero changes to their existing agent harnesses.

A code-review workflow using TypeSafe Jev that scans Git diffs or entire codebases to identify security, reliability, and correctness issues via a local dashboard.

An open-source data integration toolset that consolidates financial data sources into a unified infrastructure layer for use in AI agents, Python environments, and research dashboards.

A reimplementation of the DLSS 5 Neural Rendering runtime for AMD Radeon RX 9000 and 7000 series GPUs, enabling NVIDIA's neural rendering in DX12 games.

A cybersecurity red-teaming and robustness benchmarking suite for DeepSeek-V4 series models, using dual-layer prompt injection to test model defenses.

A Python toolchain that ships version‑controlled Codex instruction prompts (gpt‑5.6‑sol and gpt‑6‑astra) together with a reproducible regression test suite (A/B/C gates) and safe apply/rollback commands.

treg is an open‑source tool‑registry and proxy that lets AI agents call thousands of SaaS APIs and CLIs with a single token. It provides a curated catalog of priced endpoints, team‑wide secret storage, per‑call billing, and a CLI/dashboard for discovery, usage, and self‑hosting.

A collection of pre-defined capabilities and plugins that enable AI agents to interact with and manage Google Cloud and other Google developer technologies.

A set of skills and hooks for AI coding agents that forces them to communicate progress, decisions, and project state in plain, non-technical language for non-engineer builders.

A desktop and code-based platform for running and fine-tuning AI models locally, offering significantly faster training speeds and lower VRAM requirements.

A self-contained CLI tool that allows AI agents and developers to create and edit Word, Excel, and PowerPoint files without needing Microsoft Office installed.

A local-first control layer for AI coding agents that allows users to manage sessions locally by default with optional multi-device synchronization.

A high-performance, single-binary infrastructure that allows you to run Cloudflare Workers-compatible applications on your own hardware.

AirLLM is a Python library that streams model layers from disk so only one layer lives on the GPU at a time, enabling inference of 70 B‑plus LLMs on 4‑12 GB GPUs and fine‑tuning of 125 B models on < 6 GB. It supports most open‑source LLM families, optional 4‑/8‑bit block‑wise compression for speed, and works on Linux, Windows, and Apple Silicon.

A desktop enhancement tool for WorkBuddy and WorkBuddy AI that adds multi-account switching, task automation, and UI customization via CDP injection.

A rigorous autonomous research methodology and CLI that uses an audited spiral of planning and adversarial review to ensure high-integrity AI-generated code and research.

An AI-native SwiftUI component library and recipe system that provides production-ready code for LLMs to build iOS apps efficiently.

A web automation and testing framework that drives Chromium, Firefox, and WebKit with a single API, featuring dedicated integrations for AI agents and LLM-driven automation.

A menu bar application that tracks AI coding provider limits, credit balances, and reset timers across 60+ providers in one place.

An AI-powered penetration testing platform for enterprise security teams that automates vulnerability discovery, exploitation, and compliance reporting using a multi-provider LLM engine.

A high-performance tool that provides AI coding agents with ranked call graphs and codebase maps to reduce token usage and improve navigation accuracy.

An open-source LLM engineering platform for tracing, monitoring, and evaluating AI applications to streamline the development and development cycle.

A cloud-native observability platform for logs, metrics, and traces that uses Parquet columnar storage and S3 to reduce storage costs by up to 140x.

An agile framework for AI Driven Development that turns ideas into software by making planning and architectural decisions explicit and durable.

A local code knowledge graph that provides AI coding tools with precise review context via MCP, reducing token consumption by identifying the blast radius of changes.

A transformer architecture that introduces a recurrent feedback loop in the decoder to enable latent reasoning with infinite temporal depth as sequences grow.

A library of 818 structured cybersecurity skills and playbooks designed to give AI agents the domain knowledge and decision-making workflows of a senior security analyst.

A high-performance serving framework for LLMs and multimodal models that provides low-latency, high-throughput inference across single GPUs and large distributed clusters.

A local-first tool that aggregates session logs from AI coding assistants like Claude Code and Gemini CLI to track token usage and costs across models and projects.

A data visualization skill for AI agents that generates editorially-styled charts and full-page HTML reports using specific visual grammars for different reading speeds.

A self-hosted MCP server that gives ChatGPT secure access to your local files and terminal to read, edit, and run code directly in your projects.

A production-grade, Rust-native trading engine for multi-asset trading that enables a seamless transition from research to live execution using a single event-driven architecture.

A local API traffic capture tool for AI coding agents that attributes token costs to specific request components like system prompts and tool schemas.

OpenSandbox is an open‑source sandbox platform for AI agents and other code‑execution workloads. It offers multi‑language SDKs, a CLI, and a server that can run sandboxes on Docker locally or on Kubernetes at scale, with strong isolation (gVisor, Kata, Firecracker), network policies, and a credential vault. Use cases include coding agents, browser/desktop automation, RL training, and secure code‑execution services.

An open source local inference engine that profiles your hardware to recommend, download, and run the best-fitting LLMs locally and privately.