An in-process intelligence layer for AI agents that reduces costs and latency by speculatively executing queries with small models and escalating to flagship models only when needed.

A GUI application and toolkit for Claude Code that provides visual session management, custom agent creation, and usage analytics.

An automated structural MRI morphometry system that integrates CAT12 processing to measure brain tissue volumes and generate quantitative reports.

A structured meta-research skill for Claude Code that transforms research queries into a 13-phase pipeline with hypothesis testing, source triangulation, and automated verification.

Kimi AI Peak is an intelligence suite for Windows that provides access to state-of-the-art AI models and prompt engineering tools.

A programmatic marketplace that applies ad-tech economics to match consumer AI agents with provider agents through standardized bidding, discovery, and automated settlement.

A package manager and MCP gateway for AI coding agents that centralizes tool and rule configurations into a single version-controlled file for 35+ providers.

CyberCode is an open‑source, locally‑run AI coding assistant built on the Claude‑Code interaction style. It offers permanent memory, self‑evolution, a TUI, a cross‑platform desktop GUI, remote control via Telegram/Feishu, model‑agnostic provider support, code‑graph indexing, token‑optimisation, scheduled tasks, and extensible plugins/skills.

Midjourney Lab is a Windows-based machine learning platform that supports multi-modal generation and processing of text, images, audio, and video.

EvoTrace is a local‑first tool that imports Claude Code or Codex session histories, mines coherent coding episodes, and compiles them into verified, Docker‑ready tasks, preference data, and reward candidates for AI training and evaluation. It runs on the DeepSeek Harness UI, uses a four‑agent review pipeline, and keeps all data under the user’s control.

Pisper is a cross‑platform multi‑agent chat and workflow tool that lets you branch, parallelize, and automate LLM conversations. Built on the open‑source Pi Coding Agent, it offers desktop, terminal, and mobile clients, on‑demand plugins, secure local‑only data storage, and optional LAN/P2P remote linking.

A high-performance vector similarity search engine for PostgreSQL, DuckDB, and SQLite that uses a custom graph index and quantization to enable efficient ANN search.

Thumbnail Maker Lab is a professional design toolkit for creating thumbnails that combines vector graphics with AI-powered image editing and batch processing.

An evolutionary framework that evolves populations of AI agents through competition, selection, and mutation to optimize their performance against a specific goal.

ClaudeBox is a Docker‑based tool that launches Anthropic’s Claude Code AI coding assistant inside an isolated container. It provides per‑project Docker images, persistent authentication/history, and a set of pre‑configured development profiles (C/C++, Python, Rust, Go, etc.). Features include multi‑instance support, firewall allowlists, macOS clipboard bridging, tmux integration, and a simple task engine. Installation is via a self‑extracting `.run` installer that also sets up Docker if needed. Users create “slots” (persistent Claude sessions) per project, add profiles, and run Claude with custom flags, all while keeping project data isolated and reproducible.

Mysti is a VS Code extension that integrates 12 code‑generation AI providers (including Claude, Codex, Gemini, Copilot, Ollama, LocalAI, etc.) and adds collaboration features such as multi‑agent brainstorming, developer personas, autonomous execution with safety controls, @‑mention routing, and automatic context compaction. Install the extension, add at least one provider CLI (install a second for brainstorming), configure via JSON settings, and start coding with AI directly in the editor.

An open-source, self-hosted platform for tracking and optimizing brand visibility and citations across AI answer engines like ChatGPT, Perplexity, and Gemini.

A professional AI subtitling software that uses advanced ASR models and custom alignment algorithms to provide high-accuracy local transcription and translation for video editors.

A lightweight Windows AI workspace for content generation, analysis, and creative automation using various AI models.

A living wiki for codebases that uses AI agents to automatically extract and maintain architectural context and system knowledge in Markdown files within the repository.

Atomic Agent is an open‑source, local‑first AI assistant that runs on your machine using quantised models via `llama.cpp`. It executes tool‑call JSON loops to browse, edit files, run shell commands, manage memory, and more, all while keeping state on disk and offering a TUI/CLI and HTTP side‑car for integration.

An Android SDK for adding multimodal semantic search to video and image libraries, allowing users to find specific moments by meaning.

A browser-based parametric CAD system that enables collaborative mechanical design between humans and AI agents using a shared exact geometry kernel.

An open-source, self-hostable AI SOC that automates security event triage and investigation with a fully transparent, replayable audit trail of AI agent decisions.

A framework for building confidential smart contracts on EVM-compatible blockchains using Fully Homomorphic Encryption (FHE) to process encrypted data on-chain.

A passive observer for AI-written code that links git commits to the prompts and intents of coding agents to provide a decision graph of a repository.

An MCP server that connects AI clients like Claude and ChatGPT to ServiceNow, providing over 500 tools to query and automate the platform using plain English.

An open research project exploring Engram-based memory injection for LLMs and Stable Diffusion to enable parameter-efficient knowledge updates without catastrophic forgetting.

A self-learning skill layer for Claude Code that automatically distills lessons from real sessions into a maintained library of reusable skills.

A configuration-as-code platform that allows developers to define AI agent instructions, skills, and settings once and compile them into native configurations for 50 different AI coding tools.

An Android SDK that enables reliable, low-latency live video streaming from smart glasses to a cloud ingest service using a Rust-powered media core.

Golem is a distributed cloud environment for running WebAssembly components, enabling developers to build and deploy scalable agents in languages like Rust and TypeScript.

An agentic development environment that uses a Plan-Revise-Execute workflow to ensure AI agents produce high-quality code with minimal hallucinations.

BugTraceAI is an open‑source, self‑hosted platform that uses autonomous AI agents together with Go fuzzers, Playwright browsers, and classic security tools to perform bug‑bounty and penetration‑testing scans. It ships four main components—CLI scanner, React web dashboard, Docker‑based launcher, and an extensible MCP agent framework—plus a deliberately vulnerable practice app (BugStore). The system runs locally (AGPL‑3.0), supports model benchmarking, authenticated scanning, and generates detailed reports. It’s designed for hunters, DevSecOps pipelines, and security education.

An API implementation and example set for ByteDance's Seedance 2.0, enabling text, image, and multimodal reference-to-video generation with synchronized audio.

A multi-agent AI research and paper-trading framework for cryptocurrency that uses specialized analysts and a deterministic risk engine to simulate trades.

A set of communication-oriented multi-agent environments for training AI agents to coordinate, communicate, and compete in particle-based simulations.

A TypeScript meta-framework for LangGraph.js that provides file-system routing, generated types, and deterministic testing for building AI agents.

A local secret broker for coding agents that keeps sensitive credentials in an encrypted vault and prevents them from entering the agent's context.

An infrastructure governance engine that scans Kubernetes and Terraform configurations to provide security, cost, and compliance scores, featuring specialized tools for governing AI agent fleets.

An executable repository-level benchmark for automated program repair of ArkTS/OpenHarmony issues, providing 502 real-world instances and a full evaluation pipeline.

A CLI and contract system that converts prose-based agent skills into structured, auditable specifications to ensure AI agents follow safety rules and provide proof of completion.

GPA is a unified auto-regressive transformer model that integrates speech recognition (ASR) and text-to-speech (TTS) into a single system with near-SOTA performance.

A tool that audits command-line interfaces by probing runtime behavior to create an evidence-backed command index, reducing token burn and errors for AI agents using CLIs.

An autonomous, vision-grounded agent framework that allows LLMs to perceive and operate a computer screen through a perceive-reason-act loop.

ORG‑2 is a Rust‑based desktop tool that records the entire workflow of AI coding agents (prompts, tool calls, file edits, etc.), lets teams replay sessions like a video, and provides “AI‑blame” linking every line of code back to the originating agent decision. It supports 20+ agent CLIs, offers collaboration features, a built‑in terminal/Git workspace, and optional browser automation. Distributed as native installers for macOS, Windows and Linux, it is AGPL‑3.0 licensed.

A graph-canonical AI workflow language that compiles agent orchestration into deterministic graphs to reduce token costs and eliminate prompt-loop instability.

A secure infrastructure execution framework that gives AI agents a catalog of bounded, declared actions instead of a shell to maintain production authority.