Skill 与 AgentSKILLS & AGENTS· MULTI-AGENT
ownpilot/OwnPilot
Privacy-first personal AI assistant platform with autonomous agents, tool orchestration, and multi-provider support.
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.
能力CAPABILITIES
上手GET STARTED
git clone https://github.com/ownpilot/ownpilot.git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
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
需检查Needs review
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
11 OCT 202611 OCT 2026
增长GROWTH
+0.0%+0.0%
426 → 426 stars · 2 个快照426 → 426 stars · 2 snapshots
状态STATUS
持续活跃Active
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commandsreadme
- **Dual Execution Modes** — Auto mode (headless `child_process.spawn`) and interactive mode (PTY terminal)
02控制浏览器Controls a browserreadme
- **Headless Automation** — Playwright-powered Chromium for AI-driven web browsing
03读写本地文件Reads and writes local filesreadme
- **Filesystem** — Read, write, and manage local files
04读取 API KeyReads an API keyreadme
# Start OwnPilot + PostgreSQL (uses defaults, no .env needed)
05执行 Shell 命令Runs shell commandspackages/gateway/data/example-skills/api-debugging/SKILL.md
allowed-tools: Bash(curl:*)
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "cursor",
"evidence": "tree: .cursorrules/"
},
{
"agent": "claude-desktop",
"evidence": "readme: …tools as an MCP endpoint for Claude Desktop and other MCP clients - **Use…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …trate Claude Code, Codex, and Gemini CLI from the web UI or via AI too…"
}
],
"apiKey": "rated keys for api-key auth # JWT_SECRET= # For jwt auth (min",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 11,
"dev-tools": 2,
"indie-web": 0,
"skill-agent": 2,
"productivity": 4
},
"primary": "skill-agent",
"secondary": "multi-agent"
},
"localRuntime": "oint - **Local AI Support** — Ollama, LM Studio, LocalAI, and vLLM auto-disc",
"skillMdTotal": 9,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 6,
"media": 0,
"design": 1,
"browser": 1,
"devtool": 2,
"security": 4,
"marketing": 0,
"productivity": 1
},
"classification": [
{
"signal": "9 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"packages/gateway/data/example-skills/api-debugging/SKILL.md",
"packages/gateway/data/example-skills/code-review/SKILL.md",
"packages/gateway/data/example-skills/document-assistant/SKILL.md",
"packages/gateway/data/example-skills/git-workflow/SKILL.md",
"packages/gateway/data/example-skills/meeting-notes/SKILL.md",
"packages/gateway/data/example-skills/presentation-builder/SKILL.md",
"packages/gateway/data/example-skills/research-synthesizer/SKILL.md",
"packages/gateway/data/example-skills/spreadsheet-analyst/SKILL.md",
"packages/gateway/data/example-skills/writing-assistant/SKILL.md"
],
"skillMdFetched": 9
}