agentrigs
+ submit rig
~ / rigs / VoltAgent / voltagent

VoltAgent/voltagent

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

↗ GitHub ★ 10.7k mit updated 11d ago project Claude CodeCodexCursor
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~522 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/VoltAgent/voltagent

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit VoltAgent/voltagent/examples/with-workspace/workspace/skills/data-analysis .claude/skills/data-analysis
$ npx degit VoltAgent/voltagent/examples/with-workspace/workspace/skills/playwright-cli .claude/skills/playwright-cli

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (2)

Workspace Data Analystplaywright-cli

Cursor rules (1)

agents · always

Similar rigs

do-whilefor/Jase-SecKit
面向授权安全测试、AI 辅助渗透测试与漏洞研究的可复用 Security Skills 。
★ 7 project Claude CodeCodex 5 skills 2 agents 26d ago
Pragmatist 206 tok ·
HatriGt/agent-sandbox
A cloud sandbox for coding agents, on your own server. Start a run from the dashboard, from any agentic IDE (Cursor, Claude Code, Codex, VS Code), or from a script — it runs in an isolated KVM microVM and streams back live.
★ 0 project Claude Code 7 skills today
Pragmatist 391 tok ·
Vironnimo/vbot
Your own AI agents, self-hosted: persistent agents with memory that work with you or on their own, in chat, real terminals, swarms, on schedules and by voice. Any model (subscriptions, API keys, local). Browser, desktop, CLI, Telegram, Disc
★ 1 project Claude CodeCodex 10 skills 1 hooks today
Skill Collector 4.0k tok ·
exactbee/claude-code-workflow
Structured Claude Code workspace — Opus plans, Sonnet executes. Curated MCP stack with ~98% token savings on input. Drop-in template for developers.
★ 1 setup Claude Code 4 mcp 11 skills 6mo ago
Skill Collector 10.0k tok ·
copied ✓