Explore the directory

An official Tonghuashun (HiThink) data service providing A-share market quotes, financial statements, indices and other market data for AI agents, quantitative research and application development.

• APIs

A real-time, multi-user, multi-agent collaboration workspace where people and their AI coding, design and image-generation agents share context, files and apps in one room instead of hand-offs between separate tools.

• Agent frameworks

A web-based image generation and editing tool built on the OpenAI gpt-image-2.5 API, supporting reference images, mask editing, batch generation and a multi-turn agent chat mode, with data stored locally.

• Generative media

A local-first command-line search tool that unifies ripgrep-style text search, BM25 and vector search behind one interface, usable directly from a terminal or by an AI agent.

• RAG
• CLI tools

An Agent Skills collection that gives an AI agent nine methodological tools drawn from classical materialist dialectics and practice philosophy, for investigating a problem, focusing on its main contradiction and pushing work through to completion.

• Agent skills

A frozen, community-built set of DeepSeek Harness agent presets that anchored the DeepSeek V4 Pro model's tool-use behavior on a minimal starting condition before promoting it to a fuller tool catalog.

• Agent skills

A set of mandatory rules for AI coding agents that filters out generic AI-generated interface designs, copy and code, while leaving room for a project's own design direction to supply the finished look.

• Agent skills

A Chinese-localized distribution of the open-source personal AI assistant OpenClaw, translating its CLI and web dashboard and syncing hourly with upstream releases.

• Agent frameworks

A type-safe SQL builder for Go with code generation, supporting PostgreSQL, MySQL, and SQLite, plus automatic mapping of query results into Go structs.

• Databases

An efficient lifelong memory system for LLM agents that stores, compresses and retrieves long-term memories with semantic lossless compression, now covering text, image, audio and video.

• Agent memory

A portable, real-time runtime for AI agents on the JVM that streams a single agent implementation to clients over WebSocket, SSE, gRPC or WebTransport, and speaks MCP, A2A and AG-UI.

• Agent frameworks

A Python computer vision framework for self-supervised learning, offering modular loss functions and model heads with PyTorch and PyTorch Lightning-based examples for many published methods.

• Libraries

A JAX and Flax codebase for research on attention-based computer vision models, providing shared libraries for training large-scale, multi-device vision models plus complete example projects.

• Libraries

A library for quantizing and compressing large language models for deployment with vLLM, covering weight, activation, KV-cache and attention quantization with Hugging Face integration.

• Inference
• Libraries

A curated collection of books, courses, and other resources for learning programming, web development, and computer science.

• Curated lists

A Java rules and orchestration engine that drives complex business logic from DSL rule files, supporting hot reloading, multi-language scripting and, since v2.16.0, orchestrating AI agents alongside ordinary components.

• Agent frameworks
• Backend

A multi-LoRA inference server that serves thousands of fine-tuned language models from a single GPU by dynamically loading LoRA adapters onto one shared base model.

• Inference

A local context engineering layer for AI coding agents that caches, compresses and routes what gets sent to a model, tracking token and cost savings against a measured baseline.

• Agent memory

A desktop app that turns existing CLI coding agents such as Claude Code, Gemini CLI, Codex CLI and OpenClaw into one orchestrated multi-agent workspace, running tasks in parallel with real-time tracking.

• Coding agents

An open-source OpenAI- and Anthropic-compatible LLM inference server and Mac app for Apple Silicon, built on MLX and focused on reliable tool calling for coding agents.

• Coding agents
• Inference

An unofficial, community-built Linux packaging of OpenAI's official ChatGPT desktop app, repackaging the signed macOS-derived Linux payload into deb, RPM, pacman, AppImage and Nix builds.

• Inference

A free, open-source debugging tool for Claude Code that reads its local session logs and reconstructs file reads, tool calls, subagent activity, thinking content and context-window usage in a visual interface.

• Coding agents
• Debugging

A router and control center that lets the Codex CLI and desktop app, along with Claude Code, Cursor, and Gemini CLI, call external model providers such as Kimi, DeepSeek, and xAI instead of only their default backend.

• Coding agents
• LLM gateways

An open-source collection of SEO, GEO and marketing skills for AI agents such as Claude Code and Codex, covering site audits, ad platform analysis and connected WordPress or GoHighLevel changes.

• Agent skills
• Workflow automation