Skip to content

ypollak2/llm-router

v1.8.2 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo LLM Frameworks
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-routing anthropic claude claude-code cost-optimization gemini
+7 more
litellm llm llm-router mcp-server model-router ollama openai

Summary

AI summary

Headless install adds one‑command LLM Router setup with auto‑routing and dual‑mode session banner

Full changelog

What's New

  • Headless install (
    ╔══════════════════════════════════════════╗
    ║ LLM Router — One-Command Install ║
    ╚══════════════════════════════════════════╝

    ✓ Copied session-start.py → /Users/yali.pollak/.claude/hooks/llm-router-session-start.py
    ✓ Hook already registered: llm-router-session-start.py
    ✓ Copied auto-route.py → /Users/yali.pollak/.claude/hooks/llm-router-auto-route.py
    ✓ Hook already registered: llm-router-auto-route.py
    ✓ Copied agent-route.py → /Users/yali.pollak/.claude/hooks/llm-router-agent-route.py
    ✓ Hook already registered: llm-router-agent-route.py
    ✓ Copied subagent-start.py → /Users/yali.pollak/.claude/hooks/llm-router-subagent-start.py
    ✓ Hook already registered: llm-router-subagent-start.py
    ✓ Copied usage-refresh.py → /Users/yali.pollak/.claude/hooks/llm-router-usage-refresh.py
    ✓ Hook already registered: llm-router-usage-refresh.py
    ✓ Copied cc-usage-track.py → /Users/yali.pollak/.claude/hooks/llm-router-cc-usage-track.py
    ✓ Registered PostToolUse hook: llm-router-cc-usage-track.py
    ✓ Copied session-end.py → /Users/yali.pollak/.claude/hooks/llm-router-session-end.py
    ✓ Hook already registered: llm-router-session-end.py
    ✓ MCP server already registered: llm-router
    ✓ Installed routing rules → /Users/yali.pollak/.claude/rules/llm-router.md
    ✓ Registered llm-router in Claude Desktop → /Users/yali.pollak/Library/Application Support/Claude/claude_desktop_config.json

✓ LLM Router installed globally.
Every Claude Code session will now auto-route tasks.
Restart Claude Code (and Claude Desktop if installed) to activate.

Provider keys (optional — router works without any):
⬜ Claude subscription mode off (set LLM_ROUTER_CLAUDE_SUBSCRIPTION=true to enable)
✓ API keys set: OpenAI

Try it:
In Claude Code, ask: "What does os.path.join do?"
You'll see: ⚡ ROUTE → Haiku (simple query)

Subcommands:
llm-router doctor — verify everything is wired up
llm-router status — today's cost & savings
llm-router dashboard — web dashboard (localhost:7337)
llm-router install --check — preview install state
llm-router install --force — reinstall / update paths
llm-router uninstall — remove): prints Dockerfile snippet + settings.json merge for Docker/CI/K8s agent environments

  • Dual-mode session banner: API-key mode shows correct "API-key routing in effect" banner instead of subscription banner
  • No OAuth in API-key mode: session-start hook skips macOS Keychain lookup when LLM_ROUTER_CLAUDE_SUBSCRIPTION is not set — prevents noisy warnings in containers/Linux

Upgrade

pip install --upgrade claude-code-llm-router

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track ypollak2/llm-router

Get notified when new releases ship.

Sign up free

About ypollak2/llm-router

Subscription-aware LLM router for Claude Code. Routes tasks to 20+ providers (OpenAI, Gemini, Groq, Ollama, Codex) based on complexity classification, Claude subscription pressure, and cost. Free tasks stay on Claude subscription; expensive tasks fall back to the cheapest capable model. Includes 30 MCP tools, 6 auto-routing hooks, semantic dedup cache, prompt caching, daily spend cap, and a live web dashboard.

All releases →

Related context

Earlier breaking changes

  • v9.2.0 Changes auto‑route directive from advisory "DO NOT SKIP" to hard constraint with explicit blocked tools list.
  • v9.2.0 Breaks permanent downgrade of enforcement after first Edit/Write; v13 now requires per‑turn routing.

Beta — feedback welcome: [email protected]