npm
jnMetaCode/agency-agents-zh
🎭 267 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 52 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。
MITAug 5, 2026 · metrics 2.10.0
All tags
Catalogue tag
#qwen
Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.
55 records
npm
jnMetaCode/agency-orchestrator
🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 267 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 11 LLM providers (7 key-free). 一句话组建你的「一人公司」AI 专家团队，几分钟交付完整方案；验收自动核验，网页 / 桌面 / Docker 全渠道。
Apache-2.0Jul 26, 2026 · metrics 2.10.0
npm · crates.io
snomiao/agent-yes
Run AI coding agents (Claude, Codex, Gemini …) unattended — auto-answer prompts, auto-retry on rate limits, and list/tail/steer every agent locally or from agent-yes.com
MITJul 18, 2026 · metrics 2.10.0
PyPI
athola/claude-night-market
23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.
MITJul 18, 2026 · metrics 2.10.0
PyPI
jagoff/memo
Persistent semantic memory for AI agents — 100% local on Apple Silicon (MLX) or Linux/Ubuntu (CPU). Markdown source of truth, sqlite-vec + BM25 hybrid search, a codegraph-backed knowledge graph, MCP server + CLI. No cloud, no keys.
MITJul 22, 2026 · metrics 2.10.0
npm · crates.io
SeemSeam/claude_codex_bridge
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
Custom licenseJul 22, 2026 · metrics 2.10.0
npm · PyPI
invergent-ai/surogate
Training/Fine-tuning at the speed of light
Apache-2.0Jul 21, 2026 · metrics 2.10.0
npm
itayinbarr/little-coder
A harness optimized to smaller LLMs
Apache-2.0Jul 23, 2026 · metrics 2.10.0
Go · npm · PyPI
oschina/mothx
Ultra cost-effective terminal AI coding assistant with excellent token cache hit rate. Built in ~10K lines of Go, it uses DeepSeek by default with multiple modes and sandbox.
MITSep 6, 2026 · metrics 2.10.0
npm · PyPI
ZM-BAD/DAG-chat
Chat applications that use DAG to build question-answer relationships.
MITAug 19, 2026 · metrics 2.10.0
npm
jellydn/pi-clinepass-provider
ClinePass provider for pi — 11 curated open-weight coding models (GLM-5.2, Kimi K2.7 Code, Kimi K3, DeepSeek V4, Qwen3.7, and more)
MITJul 25, 2026 · metrics 2.10.0
npm · PyPI · Go
startvibecoding/mothx
Ultra cost-effective terminal AI coding assistant with excellent token cache hit rate. Built in ~10K lines of Go, it uses DeepSeek by default with multiple modes and sandbox.
MITJul 15, 2026 · metrics 2.10.0
npm
saaranshM/unsnooze
Auto-resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode & Antigravity when the 5-hour/weekly usage limit resets — tmux, Zellij, VS Code & desktop apps
MITJul 25, 2026 · metrics 2.10.0
npm
therealtimex/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MITJul 17, 2026 · metrics 2.10.0
Go
mlhher/late-cli
Stop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny local models up to Sol, Fable and Kimi K3.
Custom licenseJul 20, 2026 · metrics 2.10.0
Go
petmal/MindTrial
MindTrial: Evaluate and compare AI language models (LLMs) on text-based tasks with optional file/image attachments and tool use. Supports multiple providers (OpenAI, Google, Anthropic, DeepSeek, Mistral AI, xAI, Alibaba, Moonshot AI, OpenRouter), custom tasks in YAML, and HTML/CSV/JSON reports.
MPL-2.0Aug 30, 2026 · metrics 2.10.0
Go · npm · PyPI
startvibecoding/vibecoding
Ultra cost-effective terminal AI coding assistant with excellent token cache hit rate. Built in ~10K lines of Go, it uses DeepSeek by default with multiple modes and sandbox.
MITJul 18, 2026 · metrics 2.10.0
PyPI · npm
wesleysimplicio/simplicio-dev-cli
Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).
Custom licenseJul 31, 2026 · metrics 2.10.0
npm
runtypelabs/mixlayer-ai-provider
AI SDK provider for Mixlayer — the fully oxidized inference API
MITAug 3, 2026 · metrics 2.10.0
npm
xk1ko/aigloo
Self-hosted AI gateway. Route, translate and track requests across providers, with access keys, budgets, and a built-in dashboard.
MITJul 25, 2026 · metrics 2.10.0
npm · Go
hxz0727/api-switch
Claude Code 多模型代理 — 一键切换 DeepSeek、Qwen、GLM、Moonshot 等国产大模型，协议自动转换，零配置即用
No licenseJul 17, 2026 · metrics 2.10.0
—
maxgfr/claude-code-switch
Minimal, zero-dependency provider switching for Claude Code — switch between Anthropic, OpenRouter, DeepSeek, Z.AI, Kimi, Qwen, MiniMax and custom endpoints
MITJul 23, 2026 · metrics 2.10.0
npm
tugudush/copilot-custom-endpoints
No repository description published.
No licenseJul 22, 2026 · metrics 2.10.0
npm
sebaxzero/pi-loop-police
Pi extension — detects and interrupts infinite thinking-block and tool-call doom loops in real time
No licenseSep 5, 2026 · metrics 2.10.0
PyPI
zym9863/modelscope-image-mcp
A MCP (Model Context Protocol) server for generating images using ModelScope Qwen-Image model.
MITJul 15, 2026 · metrics 2.10.0