Skip to content

ypollak2/llm-router

v3.1.0 Feature

This release adds 5 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

Savings data now persists across sessions and accumulates correctly.

Full changelog

What's new

Cross-session savings persistence (the big fix)

  • import_savings_log() is now called on every llm_savings and llm_usage invocation — the JSONL hook writes were never being imported into SQLite (root bug since v2.x)
  • Savings data now survives session restarts and accumulates correctly across time

Host tracking

  • New host column on savings_stats table (default: claude_code)
  • usage-refresh.py hook writes host: "claude_code" in every JSONL entry
  • Foundation for per-host attribution in future versions

Yearly projection accuracy

  • Projection now uses a 30-day month-based average instead of a 7-day rolling average
  • Fallback chain: month → week → today (always uses the longest available window)

llm_auto — routing for hook-less hosts

  • New MCP tool designed for Codex CLI, Claude Desktop, GitHub Copilot
  • Flushes JSONL before routing (server-side savings tracking without hooks)
  • Shows savings envelope every 5 calls

Multi-host install support

llm-router install --host codex
llm-router install --host desktop
llm-router install --host copilot
llm-router install --host all

Prints copy-paste MCP config snippets for each host.

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]