Skip to content

ypollak2/llm-router

v3.2.0 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

Policy engine adds org/user/repo precedence, glob-based allow/block lists, per‑task cost caps and audit trail.

Full changelog

What's new

v3.2 — Policy Engine

  • Org/user/repo precedence hierarchy for model-level routing rules
  • Glob-based allow_models / block_models in ~/.llm-router/org-policy.yaml and .llm-router.yaml
  • Per-task cost caps in org policy
  • Policy audit trail in routing_decisions.policy_applied
  • New llm_policy tool: shows active policy + last 10 audit entries

v3.3 — Savings Digest

  • Period summaries (day/week/month) with spend spike detection (2× 7-day avg alert)
  • "What if router was off?" cost simulation
  • Slack / Discord / generic webhook auto-detection from URL
  • LLM_ROUTER_WEBHOOK_URL for a dedicated digest channel
  • New llm_digest tool with send=True for webhook push

v3.4 — Community Benchmarks

  • Per-task-type routing accuracy from llm_rate 👍/👎 feedback
  • Confidence tiers: ★★★ High / ★★☆ Medium / ★☆☆ Low
  • LLM_ROUTER_COMMUNITY=true enables local anonymous export
  • New llm_benchmark tool

41 total MCP tools (+3 from v3.1.0)

Upgrade

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

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]