A TypeScript SDK that enables AI agents to control Chrome browsers by writing and executing JavaScript via a persistent V8 REPL and raw CDP.

A browser extension that enhances the DeepSeek chat interface with persistent memory, custom system prompts, and tools for generating files and managing codebases.

A local workbench for A-share short-term research that combines deterministic market data analysis with AI-driven interpretation and backtesting.

A Codex-native SEO audit suite that orchestrates specialist AI agents and deterministic runners to perform technical, content, and AI-search (GEO) analysis.

SDAR is a self-distilled agentic reinforcement learning framework that unifies Agentic RL with on-policy self-distillation to improve LLM agent performance in interactive environments.

A semantic context layer for AWS that combines knowledge graphs and formal ontologies to provide AI agents with validated, business-aware context.

An open-source AI research assistant for scientists that automates data analysis, literature review, and documentation while running locally using the user's own AI API keys.

An AI desktop companion that provides customizable 3D/2D avatars and enables AI agents to control the user's computer, messaging apps, and live streams.

An AI-powered platform that integrates traditional numerology and divination systems with LLMs, featuring an MCP server for AI agents to perform professional chart casting and analysis.

An open-source, multi-tenant platform for WhatsApp and Instagram Business messaging that is AI-agent ready and self-hostable via Supabase.

An open-source Obsidian plugin that adds semantic search, an interactive knowledge graph, and an AI agent to help users discover and connect their notes.

A bundle of six AI agent skills that automate job discovery, JD analysis, resume tailoring, interview prep, and offer negotiation.

A framework for self-referential, self-improving agents that can autonomously optimize their own code to solve any computable task.

A library for constructing generative agent-based models that simulate grounded interactions among entities in physical, social, or digital environments.

A set of plugins and style guides that enable AI agents to communicate using idiomatic Russian profanity to provide more concise and emotionally honest technical summaries for developers.

A self-hostable personal iMessage assistant that uses a cloud browser to perform digital chores like booking tickets and managing groceries while keeping user secrets private.

A system for AI agents to build and maintain LLM-compiled knowledge bases, supporting parallel research, source ingestion, and structured querying.

A lightweight framework that turns coding LLMs into browser agents by allowing them to write and execute Playwright scripts in a terminal, treating code as the primary artifact of interaction.

An enterprise AI digital employee platform that provides orchestration, deployment, and runtime capabilities for AI agents with support for on-premise deployment.

A set of multi-language SDKs that let developers embed Copilot's agentic workflows and runtime into their own applications.

A desktop AI writing system for long-form fiction that uses structured memory and local semantic search to maintain narrative consistency across complex stories.

An open-source AI-powered office suite that provides native, byte-preserving editing for Microsoft Office formats and PDFs with integrated AI agents.

An experimental system for temporary, account-free collaboration rooms where humans and independently owned AI agents can exchange real-time media and tasks.

A native desktop workspace for DeepSeek Harness that integrates agentic browsing, local tools, and remote access into a single, local-first environment.

A visual conversation workbench for DeepSeek Harness that organizes chat sessions, follow-ups, and branches into an interactive, zoomable map.

A local, AI-powered chat and roleplay engine that provides immersive gaming and storytelling environments with a plug-and-play setup.

A collection of standardized skills for AI agents to generate professional diagrams, data visualizations, and technical documentation in Markdown.

A research prototype for co-authoring durable technical documents like RFCs and implementation plans using repository-grounded AI agents.

An open-source, self-hosted omnichannel customer support desk that integrates live chat and email with AI-powered automation and a knowledge base.

An official WordPress package that exposes WordPress abilities as Model Context Protocol (MCP) tools, resources, and prompts for AI agents.

An open-source AI orchestration app that lets developers run multiple agents from different providers in parallel with shared memory and unified context.

An AI-powered relationship analysis tool that processes WeChat and QQ chat logs to quantify romantic dynamics using psychological frameworks.

An autonomous research orchestration system that replaces human-led discovery with an AI-native engine capable of autonomous literature review, gap analysis, and hypothesis generation.

A local-first Markdown application that separates information capture from organization, using AI to transform scattered fragments into structured notes.

A collection of Claude Skills for quantitative trading that enables AI agents to use financial data APIs, backtesting frameworks, and strategy development tools.

A local-first, model-agnostic AI research workbench that automates the scientific loop from literature survey to paper writing with full provenance and auditability.

A collection of AI agent skills following the Agent Skills specification to assist researchers in writing, illustrating, and managing literature for NSFC grant applications.

An AI-powered multi-agent travel planning platform that creates personalized itineraries by distilling real user data from Xiaohongshu and integrating real-time weather, hotels, and mapping services.

An open-source proofreading software that detects grammatical and stylistic errors across 20+ languages, surpassing the capabilities of basic spell checkers.

An MCP server that enables AI assistants to interact with Obsidian vaults by reading, searching, and editing notes via the Local REST API plugin.

An MCP server that enables AI assistants to search, create, and update content in Jira and Confluence across Cloud and Server/Data Center deployments.

A toolkit for automatically discovering and improving AI skills and prompts for coding agents, evolving general agents into specialists using benchmark-driven feedback.

A lightweight memory management framework for LLMs and AI agents that provides efficient long-term memory storage, retrieval, and update mechanisms.

A visual context management tool that uses a graph-based interface to let users explicitly control and prune what an LLM sees, reducing hallucinations and wasted tokens.

An agentic LLM designed for autonomous data science, capable of automating the entire pipeline from data preparation to the generation of professional research reports.

A modular, retrieval‑augmented prompt framework for AI‑assisted Chinese web‑novel writing. It splits the workflow into a short router (`SKILL.md`) and many self‑contained sub‑skills (concept planning, opening, plot logic, dialogue, consistency review, etc.). Each sub‑skill ships tutorials, runtime rules, good/bad examples, and may use local novel corpora via a provided search script. The system routes a user’s brief idea to the appropriate module, pulls relevant example excerpts, composes a concise prompt, generates text, and finally runs a consistency review. Designed for Chinese novel authors, prompt engineers, and researchers interested in modular LLM writing pipelines.

JIT-Agent is a meta-agent that dynamically generates and evolves task-specific executable harnesses to optimize the performance of agentic LLMs.

An LLM-routing coding agent that dynamically assigns development tasks to the best-suited model across different providers like Gemini, ChatGPT, and Claude.