An open-source desktop workbench for the local Grok Build CLI that provides a visual interface for managing AI agent sessions, code editing, and remote IM connectivity.

A full-stack React framework for building type-safe MCP apps and servers that enable rich, interactive UI views within AI clients like Claude and ChatGPT.

KServe is a standardized distributed inference platform for Kubernetes that enables scalable deployment of both generative and predictive AI models across multiple frameworks.

A highly customizable status line formatter for the Claude Code CLI that displays model info, token usage, git branch, and other session metrics in the terminal.

A plugin providing 35 AI coding skills that implements a structured loop of brainstorming, planning, and reviewing to capture and compound engineering knowledge within a codebase.

A unified platform for AI development and deployment featuring the Mojo programming language and the MAX framework for high-performance model serving.

A flexible and efficient RL training library for LLMs that simplifies the implementation of RLHF algorithms and scales to trillion-parameter models.

A project context and engineering control plane that provides AI coding agents with durable project knowledge, governance, and risk-driven quality gates.

A security research project focused on red teaming AI models to identify and test vulnerabilities in their safety filters.

A local model gateway and control plane that centralizes the management of multiple AI coding agents and LLM providers through a single endpoint.

A tool for batch downloading WeChat Official Account articles, comments, and media into various formats like Markdown and PDF, featuring MCP support for AI integration.

Warp is an agentic development environment based on the terminal that integrates AI coding agents to automate tasks like issue triaging, spec writing, and implementation.

An open-source generative BI engine that provides a governed semantic layer for AI agents to turn business questions into correct SQL and deployable dashboards.

Repomix converts a repository into a single formatted file (XML/Markdown/JSON) to feed codebases into LLMs, with token counting, compression, secret filtering, and git-aware filtering.

A programmable routing layer for Mixture-of-Models systems that optimizes LLM request routing across heterogeneous compute and infrastructure to improve cost, latency, and quality.

A collection of 33 modular markdown-based skills and hooks that provide coding agents with professional software engineering procedures to improve reliability and scale.

An autonomous multi-agent framework that automates the research and development loop of proposing and implementing models and data features for ML engineering and quantitative finance.

A local desktop workspace that lets users configure and run multiple coding-agent CLIs from a single interface, managing API profiles and project sessions.

An open-source LLM evaluation framework that provides unit-testing capabilities for AI agents, RAG pipelines, and chatbots using LLM-as-a-judge metrics.

An interactive terminal UI plugin for DeepSeek Harness that adds visual enhancements, image rendering, and advanced session management to the terminal experience.

An open-source red teaming framework for LLM systems that simulates adversarial attacks to uncover vulnerabilities and provides guardrails for production security.

A Go-based tool that detects anti-detect browsers and bots by scoring how coherent a browser environment is, identifying contradictions in its reported hardware and software surfaces.

An open-source kernel for AI agents that enables 100% on-device execution with crash recovery, formal verification, and NPU acceleration.

A terminal-first agentic development environment that manages persistent CLI AI agent sessions across local and remote machines with mobile monitoring.

An enterprise-grade reinforcement learning framework for large-scale model post-training, optimizing throughput and stability for trillion-parameter models.

A modern open-source Linux server management panel that provides a web GUI for server operations and a unified platform for managing AI models and agents.

A TypeScript library for orchestrating AI coding agents in isolated sandboxes, automating sandbox lifecycle and git branch management.

A self-hosted sandbox platform for AI agents that provides permanent, low-cost Linux environments with automatic lifecycle management and E2B SDK compatibility.

An AI skills manager for Obsidian that allows users to browse, create, and manage skills, commands, and rules across 17 different AI coding agents.

A containerised vLLM deployment of the EXL3‑quantised GLM‑5.3‑Flash model, tuned for 2‑4 × DGX Spark GPUs. It offers fast long‑context pre‑fill (≈1.5 k tok/s on 256 k‑token prompts), high‑throughput decode, optional FP8 dense‑weight and adaptive‑verification speed‑ups, and an optional “abliteration” edit that changes refusal behavior without rebuilding the checkpoint.

A load balancer and API proxy for ChatGPT accounts that pools multiple accounts to manage rate limits and track usage via a dashboard.

CyberStrike is an open‑source AI agent that turns any LLM (Claude, GPT, Gemini, etc.) into an autonomous penetration‑testing platform. It adds a security‑focused “intelligence layer”, ships 13+ specialised agents and 7,600+ signed security‑skill files, supports 150+ AI providers (including offline models), and can orchestrate real tools locally or on remote Bolt servers. A TUI, optional web UI, and built‑in HackBrowser complete the workflow.

An open-source, real-time infrastructure monitoring platform that provides per-second metrics and ML-powered anomaly detection with zero configuration.

A unified CLI for all Google Workspace APIs that dynamically generates its command surface, providing structured JSON output for both humans and AI agents.

A shared project memory and token optimization layer for AI coding agents that prevents redundant reads and condenses oversized bash output to reduce costs.

Principia is an autonomous scientific discovery workbench that connects scientific literature and local datasets to discover interpretable, evidence-backed mathematical rules and relationships.

A bridge that connects AI agents running on a local machine to instant messaging platforms like Telegram, Slack, and Discord for remote control.

A tool for running multiple AI coding agents in parallel using isolated, sandboxed virtual environments hosted locally or in the cloud.

A fast and memory-efficient implementation of the attention mechanism for Transformers, reducing memory IO to accelerate LLM training and inference.

An open-source product OS that combines analytics, session replays, and AI-driven automation to help teams diagnose problems and ship fixes automatically.

An AI-assisted PCB design plugin for KiCAD 10 that allows AI assistants to directly create schematics and layout PCBs via the Model Context Protocol.

An experimental Vulkan 1.4 implementation that replaces traditional graphics API abstractions with GPU pointers and application-owned descriptor heaps to simplify GPU programming.

A 1-click launcher for open-source projects that provides a user-friendly UI to automate the installation and execution of terminal-based software.

A unified cross-platform desktop application for AI-assisted annotation of text, image, video, and multimodal data, integrating state-of-the-art deep learning models to automate labeling.

An AI-powered manager for GitHub stars that uses semantic search, AI categorization, and release tracking to turn a pile of starred repositories into a structured library.

A local review tool that provides adaptive UIs for reviewing AI-generated plans, code diffs, and live web apps, allowing users to send feedback directly back to AI agents.

A tool for injecting custom, revocable instructions into Codex AI programming tools to customize behavior in new conversations without modifying the software.

A local-first web intelligence engine for AI agents that provides keyless search, crawling, and data extraction without cloud API costs or privacy concerns.