ECC (Efficient Claude Code) is an open-source performance optimization framework for AI coding agents. It analyzes agent execution patterns, identifies token waste, reduces redundant tool calls, and optimizes prompt routing to cut costs and improve speed. With 199K+ GitHub stars and +918 stars/day velocity, it has become the standard performance layer for teams running agentic coding at scale. ECC works as a middleware between your agent harness and the underlying model API, providing real-time profiling dashboards, automatic prompt compression, and intelligent caching of repeated tool call patterns. Built by affaan-m, it supports Claude Code, Codex, Gemini CLI, and any OpenAI-compatible endpoint.
Persistent memory layer for AI coding agents — benchmark-backed (95.2% on LongMemEval-S), 92% fewer tokens per session vs full-context pasting, zero manual memory.add() calls.
Open-source AI pair programming tool that works in your terminal to edit code across your entire repository.
Open-source Python library by Andrew Ng that provides a unified interface to multiple LLM providers with a simple, consistent API.