A decision engine and orchestration framework for spec-driven AI development that ensures software stability by requiring human-led decisions before AI agents execute tasks.

An open-source financial toolkit providing over 500 transparent calculation methods for financial metrics, eliminating reliance on inconsistent proprietary data sources.

pxpipe is a local proxy that compresses large text context (system prompts, tool outputs, old chat history) into PNG images before sending requests to vision‑enabled LLMs like Claude Code and Gemini, typically saving ~60‑70 % of input tokens. It includes a dashboard, offline export, and a Node API, but the rendering is lossy and works best on dense, code‑like content.

A security auditor for AI agent configurations that scans Claude Code setups for secrets, permission misconfigurations, and prompt injection vectors.

DarkMoon is an open‑source, self‑hosted platform that uses a fleet of AI agents to run fully automated penetration tests. It orchestrates 50+ real offensive tools via a secure “MCP” gatekeeper, masks all sensitive data before it reaches the language model, and returns reproducible proof for every vulnerability. Supports web, cloud, AD, Kubernetes, databases, IoT and AI/LLM endpoints, runs on local LLMs for privacy, and is GPL‑3.0 licensed.

An MCP server and CLI that provides AI agents with tools to build and test iOS and macOS projects using xcodebuild.

A TUI monitoring dashboard for AI coding agents that tracks token usage, context windows, and rate limits across multiple active sessions.

An open-source team chat system deployed on Cloudflare Workers that allows users to create independent chat spaces without maintaining a server.

A curated ecosystem of plugins, tools, and infrastructure for DeepSeek Harness, enabling users to extend AI agent capabilities through community-developed extensions.

ONNX is an open, framework‑agnostic model format and reference implementation that lets you move AI models between tools and runtimes. Install via `pip install onnx`, use the Python API to build or load a graph, then run inference with any ONNX‑compatible engine.

A Kubernetes-native batch scheduling system that optimizes resource management for AI, machine learning, and Big Data workloads.

A runtime substrate for AI agents that provides secure sandboxing, reversible execution traces, and a review-and-approve workflow for all filesystem changes.

A lightweight block diffusion model for speculative decoding that enables efficient, high-quality parallel drafting to speed up LLM generation.

Agent Chat UI is a Next.js front‑end that lets you chat with any LangGraph server. Configure the server URL, assistant ID, and optional LangSmith key, then use the web UI to send messages, stream LLM replies, hide unwanted output via special tags, and display extra “artifacts” in a side panel. The repo includes a quick‑start (`npx create-agent-chat-app`), environment‑variable shortcuts, and production guidance (API‑passthrough proxy or custom authentication).

AgentDojo is a dynamic environment and benchmark for evaluating prompt injection attacks and defenses for LLM agents.

A toolkit and MCP server that indexes local code repositories into a graph database to provide AI agents and developers with structural context like call chains and class hierarchies.

A sovereign AI agents platform for deploying and managing autonomous agents in isolated Docker containers on your own infrastructure.

Kelos is an open‑source Kubernetes controller that lets you run LLM‑based coding agents as Pods/Jobs. It defines custom resources (Workspace, AgentConfig, Task, Session, etc.) to describe code repositories, credentials, prompts, and execution policies. The controller creates isolated workloads, supports event‑driven spawning, interactive sessions, and integrates with GitHub/Jira/webhooks. Install via Helm, use the `kelos` CLI to create Workspaces and Tasks, and optionally connect through a web console.

An open-source control plane for AI coding agents that allows users to coordinate multiple parallel workers via a shared kanban board, scheduling, and a unified dashboard.

A set of AI-compatible skills that enable coding assistants to autonomously control compilers, debuggers, and communication buses for embedded hardware development.

A highly efficient gradient boosting framework that uses tree-based learning algorithms to handle large-scale data with high speed and low memory usage.

A centralized registry and API for Model Context Protocol (MCP) servers, functioning as an app store for discovery and integration.

A Python library for portfolio optimization and risk management built on scikit-learn, providing tools for factor model construction and ML-based model selection.

A multi-protocol, cloud-native industrial IoT platform that integrates AI agents for natural-language device management and data analysis.

An open-source security layer that provides antivirus-style runtime protection for AI agents, blocking risky actions like secret leaks and unsafe commands.

An AI operations agent that automates infrastructure root cause analysis and remediation, accessible via Slack or Telegram.

An AI coding framework that teaches agents your specific coding patterns to generate production-ready code that requires no refactoring, featuring human-guided approval gates and token-efficient context management.

A network traffic capture and analysis tool that uses AI to automate protocol reverse engineering and API documentation from browsers, apps, and devices.

An open-source, local-first diagramming studio that combines a visual canvas with bidirectional diagram-as-code and AI-driven generation.

A persistent memory system for AI coding agents that uses a local vector database to retain long-term technical context and user preferences across sessions.

A unified control plane and gateway for AI assets, providing centralized discovery, governance, and secure access to MCP servers, agents, and model inference endpoints.

An SLO-aware benchmarking and evaluation platform that simulates real-world workloads to optimize LLM inference performance, resource needs, and operational limits.

A high-performance VM manager for Windows and macOS that provides GPU-accelerated isolated desktops for software testing and running computer-use AI agents.

A desktop skill manager for AI coding tools that centralizes the installation, synchronization, and management of skills, MCP servers, and plugins across multiple AI agents.

A standard Python library and API for developing and comparing reinforcement learning algorithms across a wide variety of simulated environments.

A local MCP server that enables AI agents to perform deep literature research on arXiv, featuring section-level LaTeX reading, citation tracking, and topic monitoring.

A distributed LLM serving system that pools GPUs and memory across multiple machines to run large models via an OpenAI-compatible API.

GitHub Agentic Workflows (gh-aw) is an official GitHub CLI extension that lets developers define AI-powered repository automation in Markdown with YAML frontmatter, then compile and run those agentic workflows securely through GitHub Actions.

A context engineering tool that converts entire codebases into structured LLM prompts, automating the process of gathering and formatting code for AI models.

An MCP server that connects Figma design data to AI coding agents, enabling them to generate accurate code and modify designs based on design system context.

A collection of custom nodes and interface improvements for ComfyUI that simplifies complex workflows through better organization, advanced switching, and condensed loaders.

A framework for large-scale asynchronous reinforcement learning designed to train frontier models with 1T+ parameters on up to 1000+ GPUs.

A lightweight system that helps developers align AI agents with their codebase's specific standards and patterns to ensure consistent, high-quality builds.

TensorSharp is a native .NET engine that runs GGUF‑format LLMs, diffusion‑based image/video generation, and multimodal models on CUDA, Vulkan, Metal, Apple‑MLX, or pure C# CPU. It matches or beats llama.cpp, supports continuous batching, paged KV caches, tensor‑parallelism, speculative decoding, tool‑calling/agent skills, and provides Ollama/OpenAI‑compatible APIs and a web UI.

An API service wrapper for Docling that enables AI-driven document conversion via a scalable web server and REST API.

An observability and automated fixing platform that helps developers make AI agents self-healing by capturing traces, grouping failures, and dispatching coding agents to implement fixes.

A comprehensive retrieval toolkit for search and RAG that provides state-of-the-art embedding models and rerankers for text and multimodal data.

A CLI tool that converts websites into a compact, numbered format for AI agents to browse the web without burning excessive tokens.