#token-optimization

Cloud LM Provider — AWS Bedrock & Azure OpenAIfor GitHub Copilot

suddhu-iith2004

🚀 The #1 extension for enterprise AI in VS Code! Bring Claude 4.5, GPT-4o, Nova, DeepSeek & 50+ models into Copilot Chat. Features Headroom AI compression that saves 30-45% on API costs. Secure, fast, with full streaming, tool calling & vision support.

Compressor — AI Token Savings

aStudioPlus

Save tokens in GitHub Copilot agent mode — compressed read/search/outline tools, a savings ticker & report, and instruction-pack management. No network calls.

Badgr Auto — Token Optimization, Smart Routing, Local Models & Receipts

aibadgr

Cut AI coding costs with token optimization — strip repeated context on every request. Then route across local models, cheaper cloud tiers, and premium fallbacks. Track savings, latency, and receipts in VS Code.

PAER — Persistent Autonomous Engineering Runtime

brpavan-kotlin-analyzer

Token-minimising autonomous coding agent for Kotlin/Spring Boot repos. Integrates with GitHub Copilot via MCP (Model Context Protocol).

ModelBound — AI Context, Skills & MCP Sync for Cursor

ModelBound

Cursor rules sync, .cursorrules manager, and system prompt version control. Sync AI skills, rules, and knowledge bases between your IDE and ModelBound.co via MCP. Works with Cursor, Claude Code, Kiro, and Copilot.

LatentGate — Local-First AI Compression

KathanModh259

Compress images, text, conversations, and documents locally via Ollama before sending to cloud LLMs. Save ~80% on token costs.