Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
Dulus
KevRojo/Dulus
面向AI重度用户的省钱智能代理，可跑在命令行、网页、Telegram里。Dulus Ai — Agentic AI, 100% cache hit rate, Dulus is made to save you money [Gui, Web, Cli, Telegram, 2,000 MCP, 100K Skills . LiteLLM (100+ providers), local models via Ollama, /lang in 34 languages, Mesa Redonda, I create the first utility coin that can be used 100% as AI quota or Fuel, is called $Dulus
根据公开文档整理，未运行实测；费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
- 适用平台Platforms
- claude-code · opencode
- 已识别的要求Documented requirements
- API key · Local runtime
- 许可LICENSE
- GPL-3.0
能力CAPABILITIES
它能帮你做成什么What it helps you do
- 01
装好后输dulus进入对话界面
- 02
登录后生成密钥，当OpenAI接口用
- 03
一条命令让AI读代码仓库并讲解
- 04
让AI按你的话改代码并跑测试
- 05
用手机或电脑本地跑小模型，断网也能对话
上手GET STARTED
怎么装How to install
pip install -U dulus选择与你的环境对应的方式。命令来自项目文档，未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
限制与风险Limits and risk
以下要求与风险来自文档静态检查，未执行项目代码；扫描没有命中，不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
- 01需要 API KeyREQUIRES API KEY
- 是Yes
- 02需要本地环境NEEDS LOCAL RUNTIME
- 是Yes
- 03需要 DockerNEEDS DOCKER
- 未在文档中发现Not found in the docs
- 04难度DIFFICULTY
- 需要本地环境Needs a local runtime
- 05许可LICENSE
- GPL-3.0GPL-3.0
- 06阶段STAGE
- 持续活跃Active
- 创建于 05 MAY 2026Created 05 MAY 2026
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
curl -fsSL https://raw.githubusercontent.com/KevRojo/Dulus/main/install.sh | bash
02控制浏览器Controls a browserreadme
"playwright": {03控制浏览器Controls a browserskill/bundled/obsidian-cli/SKILL.md
Run `obsidian help` to see additional developer commands including CDP and debugger controls.
静态扫描发现高风险：安装脚本通过 curl 管道直接执行远程脚本（curl ... | bash），存在供应链风险；另有中风险涉及控制浏览器的能力。仅核验官方页面，未审计服务端代码；数据处理和费用以官网为准。
项目动态PROJECT ACTIVITY
它现在处在什么位置Where it stands right now
首次发现FIRST SEEN
26 OCT 202626 OCT 2026
增长GROWTH
+17.6%+17.6%
433 → 509 stars · 8 个快照433 → 509 stars · 8 snapshots
状态STATUS
持续活跃Active
质量 B+Quality B+
项目近7天有18次提交，开发活跃，功能变化快。
PROVENANCE · 这些结论的依据是什么Where these conclusions come from
- 来源 URLSource URL
- https://github.com/KevRojo/Dulus
- 原始数据哈希Raw data hash
- a7c73e773c29e779136ae1046fc205d7
- 解析时间Parsed at
- 2026-10-31T23:51:42.756Z
- 最后一次验证Last verified
- 2026-11-02T22:14:53.144Z
- 增长测量时间Growth measured
- 2026-10-30T00:09:08.210Z
- 发现查询Discovery queries
- focus:token:code:save-tokens
- 分类来源Category source
- rules
- 焦点Focus
- token (4)
完整解析证据 JSONFull parse evidence JSON
{
"agents": [
{
"agent": "claude-code",
"evidence": "install: claude CLI command"
},
{
"agent": "opencode",
"evidence": "readme: …facing byte | Frames use the OpenCode event-stream dialect, so a co…"
}
],
"apiKey": "mpatible at the router export OPENAI_API_KEY='dulus_sk_...' # the key you j",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 3,
"dev-tools": 5,
"indie-web": 0,
"skill-agent": 0,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "Auth. - **Local & offline** — Ollama, LM Studio, or the on-device `edge` run",
"skillMdTotal": 6,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 2,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 1
},
"classification": [
{
"signal": "6 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "python dependency on mcp / fastmcp + MCP framing",
"weight": 0.8
},
{
"signal": "README ships an mcpServers config for this server",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skill/bundled/defuddle/SKILL.md",
"skill/bundled/json-canvas/SKILL.md",
"skill/bundled/obsidian-bases/SKILL.md",
"skill/bundled/obsidian-cli/SKILL.md",
"skill/bundled/obsidian-markdown/SKILL.md",
"skill/bundled/unbroker/SKILL.md"
],
"skillMdFetched": 6
}