agentrigs
+ submit rig
~ / rigs / ypollak2 / llm-router

ypollak2/llm-router

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.

↗ GitHub ★ 96 mit updated 1d ago project Claude CodeCopilot Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~5.9k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add llm_router -- npx -y llm-routing
$ claude mcp add llm-router -e LLM_ROUTER_PROFILE=YOUR_LLM_ROUTER_PROFILE -- uvx claude-code-llm-router
$ npx degit ypollak2/llm-router/.claude ./rig-llm-router  # inspect, then merge into .claude/

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.

$ claude mcp add llm_router -- npx -y llm-routing
$ claude mcp add llm-router -e LLM_ROUTER_PROFILE=YOUR_LLM_ROUTER_PROFILE -- uvx claude-code-llm-router
$ npx degit ypollak2/llm-router/skills/release .claude/skills/release
$ npx degit ypollak2/llm-router/skills/route .claude/skills/route
$ npx degit ypollak2/llm-router/skills/routing .claude/skills/routing
$ npx degit ypollak2/llm-router/skills/savings .claude/skills/savings

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 *)"
    ]
  }
}

MCP servers (2)

serversourceest. tokens
llm-routing · "llm_router" npm 2.5k
claude-code-llm-router · "llm-router"
env: LLM_ROUTER_PROFILE
 pypi 2.5k

Skills (4)

releaserouteroutingsavings

Similar rigs

eugene1g/agent-safehouse
Sandbox your local AI agents so they can read/write only what they need
★ 2,086 project Claude CodeCodex 1 skills 9d ago
Minimalist 1.5k tok ·
jgravelle/jdocmunch-mcp
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
★ 204 project Claude Code 1 skills 14d ago
Pragmatist 18.0k tok ·
movieclaw/MovieClaw
Next-gen AI media server. One container replaces Sonarr, Radarr, Prowlarr, Bazarr, Jellyseerr and Jellyfin, with a web app, a native iPhone app, and an AI agent that gets things done. Free for personal use.
★ 152 project Claude CodeCodex 1 skills today
Minimalist 305 tok ·
mochow13/keen-code
A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MCPs, Subagents, Agent Skills, controllable tool output retention, hashline edits, and more.
★ 70 project Claude CodeCodex 1 skills 8d ago
Minimalist 342 tok ·
copied ✓