A span-level grounding verifier that localizes unsupported or fabricated parts of RAG, code-agent, and tool-grounded AI outputs using encoder and generative models.

incur is a TypeScript library that lets you build command‑line tools that are easy for LLM agents to discover and use. It provides typed command definitions (via Zod), token‑efficient TOON output, built‑in MCP and skill‑file generation, and can wrap or expose HTTP APIs as CLI commands.

TorchNPU is a PyTorch adapter plugin that enables the PyTorch framework to run on Huawei Ascend AI processors, providing optimized compute and distributed training capabilities.

An extension for the Pi coding agent that enables it to run interactive CLIs and subagents in an observable TUI overlay, allowing for real-time monitoring and user takeover.

A knowledge base and plugin for AI coding tools that provides verified reference guides and source code to help agents generate accurate, high-performance Jetpack Compose code.

A benchmark for evaluating document parsing tools to ensure they convert PDFs into structured output that AI agents can reliably use for autonomous decisions.

A unified runtime for MCP servers that aggregates multiple servers into one process and provides a progressive discovery workflow to prevent agent context sprawl.

A collection of custom ComfyUI nodes that streamline image generation and editing, featuring specialized support for Krea 2 and Ideogram 4 models.

A linguistic linter for Traditional Chinese (zh-TW) that enforces Taiwan Ministry of Education standards to prevent AI-generated text from using Mainland Chinese regionalisms.

Better Agent Terminal (BAT) is a cross‑platform desktop app (Windows/macOS/Linux) built with Tauri 2 and React. It lets you manage multiple project workspaces, each with split‑panel terminals, a file browser, Git viewer, snippet manager, and an embedded AI coding assistant (Claude Code or OpenAI Codex). The AI runs inside the app, offering streaming output, permission modes, session resume/fork, and detailed usage stats. Optional integration with the `cx` CLI provides lightweight semantic code navigation. Install via Homebrew, AppImage, or a one‑line script; you can also build from source with Rust and Node. Ideal for developers who want a single window to run commands and interact with LLMs safely and efficiently.

GrokSearch‑rs is a Rust‑based MCP server that adds live, cited web‑search tools to LLM agents. It can run locally via stdio or be exposed as a multi‑tenant HTTP service. The server queries a configurable chain of providers (Tavily, Exa, TinyFish, Firecrawl) and includes key‑free specialist extractors for GitHub, StackExchange, arXiv, and Wikipedia. Features include response budgeting, caching, OAuth support for Grok, and a health‑check `doctor` tool. Install via npm (pre‑built binary) or Docker, configure with env vars or a global TOML file, and integrate with Claude‑style assistants through the MCP protocol.

A self-learning plugin for AstrBot that allows bots to autonomously acquire group-specific slang, expression styles, and social relationships from chat history to evolve their persona.

A monitoring and observability dashboard for AI coding agents that tracks tool calls, costs, and session trajectories across 32 different runtimes without requiring code changes.

A high-performance Go-based AI backend for ESP32 devices that enables low-latency, full-streaming voice interactions by integrating ASR, LLM, and TTS engines.

An open-source GRC engineering toolkit for Claude that automates evidence collection, gap assessment, and remediation across multiple compliance frameworks.

A collection of on-device demo apps for iOS, Android, and HarmonyOS that allow the MiniCPM-V family of multimodal and text models to run fully locally via llama.cpp.

A lightweight, hackable navigation system for robots that provides real-time mapping, localization, and planning across multiple robot and compute platforms.

A neural video codec that provides real-time performance and high compression efficiency across Apple, Intel, and Qualcomm NPUs.

An AI governance platform that helps businesses manage AI compliance, risk, and security through on-premises hosting and support for frameworks like the EU AI Act.

Octafuse Gateway is an open‑source, self‑hosted AI gateway that unifies access to multiple model providers (OpenAI, Anthropic, Gemini, DashScope, etc.) and agent tools behind a single OpenAI‑compatible API. It offers one‑click provider/model import, protocol translation, four routing strategies, detailed user/quota/billing management, an admin UI, and can be deployed via Docker or Cloudflare Workers.

An AI-powered equity research framework that transforms AI agents into institutional-grade analysts by enforcing rigorous valuation, forensic accounting, and industry-specific research protocols.

A TUI-based model manager and server launcher that auto-detects inference backends and local model files to simplify serving LLMs.

An AI-powered market analysis tool that consolidates technicals, fundamentals, and portfolio management into a conversational interface for traders.

An AI agent self-improvement harness that turns user corrections and successful interaction paths into persisted behavioral improvements and shared playbooks.

A local-first AI workspace and orchestration layer that provides project-scoped agents with persistent memory, files, and pipeline capabilities.

A visual editor for your codebase that lets you to select UI elements in a live browser preview and use AI agents to edit the source code directly.

A React Native Expo UI kit featuring 10 high-fidelity animated welcome and onboarding screens inspired by leading iOS apps, designed for educational study and integration via AI coding agents.

An OpenVINO-powered inference engine for Intel devices that serves LLMs, VLMs, and audio models via OpenAI-compatible endpoints.

A production-ready C++ inference engine that provides a unified API for the entire YOLO family, supporting tasks from object detection to metric depth estimation.

A durable memory system for coding agents that records session events to a local log and allows agents to search for relevant prior context to handle long-horizon tasks.

An open-source wheeled biped robot platform with hardware build instructions and a Python library for balancing and locomotion control.

openTCS is an open-source framework for controlling fleets of automated guided vehicles and mobile robots, providing core algorithms for routing, dispatching, and scheduling.

A collection of implementation examples for the ros2_control framework, demonstrating how to build hardware interfaces and controllers for various robot types.

An AI assistant for reMarkable tablets that captures handwritten input via screenshots and responds by drawing or typing directly back onto the screen.

A lightweight and highly accurate wake word engine for building always-listening voice-enabled applications across IoT, mobile, and web platforms.

Ix is a system intelligence tool that parses codebases into a persistent graph of symbols and relationships, allowing humans and AI agents to query structure instead of searching text.

An AI-powered code completion plugin for Neovim that supports multiple LLM providers and various completion frontends like virtual text and nvim-cmp.

An autonomous LLM-driven agent that solves complex tasks by breaking them down into subtasks and executing them safely within a Docker-sandboxed environment.

CoVT is a framework that enables Vision-Language Models to reason using continuous visual tokens, improving their spatial reasoning and geometric awareness by grounding semantic thoughts in perceptual cues.

A GPU-accelerated library for vector similarity search and clustering, providing high-performance implementations of approximate nearest neighbors algorithms for AI and data mining.

A modern intelligent dialogue system that enables the creation and management of AI agents with multi-agent collaboration, RAG, and a three-layer memory architecture.

A Rust-based OpenSCAD editor and compiler that uses exact CSG and hyperreal numbers for precision, featuring interactive visualization and AI-assisted design revisions.

A file-backed workflow and runtime for AI agents that replaces chat memory with repository-local artifacts to ensure continuity and consistency across sessions.

A Chrome extension that adds a native AI layer to the browser, integrating multiple LLM providers and enabling agentic browser control and external MCP tool support.

A structural code navigation tool and MCP server that helps AI agents read codebases more efficiently by providing outlines, definition-first search, and call-chain tracing.

A security scanning tool for Model Context Protocol (MCP) servers and tools that uses YARA, LLMs, and Cisco AI Defense to detect malicious behavior and vulnerabilities.

An open-source mobile app for Android and iOS that enables private, on-device LLM chat, image generation, and video generation using hardware acceleration.

A high-performance job queue for Bun that replaces Redis with SQLite or PostgreSQL, featuring a built-in workflow engine and native MCP support for AI agents.