Skip to content

ypollak2/llm-router

v8.7.0 Feature

This release adds 5 notable features for engineering teams evaluating rollout.

Published 20d 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

Replaces ANSI output with a Rich-rendered two‑column Cyber‑Grid dashboard.

Changes in this release

Feature Medium

Intelligence panel added with routing method breakdown and Claude quota delta tracking.

Intelligence panel added with routing method breakdown and Claude quota delta tracking.

Source: llm_adapter@2026-05-21

Confidence: high

Feature Medium

Financial panel added showing period savings grid, cost comparison, and yearly projection.

Financial panel added showing period savings grid, cost comparison, and yearly projection.

Source: llm_adapter@2026-05-21

Confidence: high

Feature Medium

L14 Activity panel displays Braille Unicode call volume chart with quality metrics.

L14 Activity panel displays Braille Unicode call volume chart with quality metrics.

Source: llm_adapter@2026-05-21

Confidence: high

Feature Medium

Wildcard Insight provides auto-generated cost-saving suggestions based on routing data.

Wildcard Insight provides auto-generated cost-saving suggestions based on routing data.

Source: llm_adapter@2026-05-21

Confidence: high

Feature Medium

Tokyo Night true-color hex palette with 4-tier brightness hierarchy implemented.

Tokyo Night true-color hex palette with 4-tier brightness hierarchy implemented.

Source: llm_adapter@2026-05-21

Confidence: high

Feature Medium

Clean-break separator rule added before dashboard with session timestamp.

Clean-break separator rule added before dashboard with session timestamp.

Source: llm_adapter@2026-05-21

Confidence: high

Dependency Medium

Upgrade command provided for pip install --upgrade claude-code-llm-router.

Upgrade command provided for pip install --upgrade claude-code-llm-router.

Source: llm_adapter@2026-05-21

Confidence: low

Refactor Medium

Provides graceful fallback to legacy renderer if Rich is unavailable.

Provides graceful fallback to legacy renderer if Rich is unavailable.

Source: granite4.1:30b@2026-05-22-audit

Confidence: high

Refactor Medium

Session-end output replaced with Rich-rendered, two-column Cyber-Grid layout.

Session-end output replaced with Rich-rendered, two-column Cyber-Grid layout.

Source: llm_adapter@2026-05-21

Confidence: low

Full changelog

Cyber-Grid Static Dashboard

Replaces the plain ANSI session-end output with a Rich-rendered, two-column "Cyber-Grid" layout.

Added

  • Intelligence panel (left): routing method breakdown with zero-cost gauge, Claude subscription quota bars with delta tracking
  • Financial panel (right): period savings grid with token counts, baseline vs actual cost comparison with percentage badge, yearly projection
  • L14 Activity panel: Braille Unicode chart (U+2800) for 14-day call volume with quality metrics (fallbacks, routing latency, cache hit rate)
  • Wildcard Insight: auto-generated cost-saving suggestion based on routing data
  • Tokyo Night true-color hex palette with 4-tier brightness hierarchy
  • Clean-break separator rule before dashboard with session timestamp
  • Graceful fallback to legacy renderer if Rich unavailable

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]