A skill that helps an LLM keep its context lean working within large project repositories, managing its dependencies, tools and data.
-
Updated
Nov 8, 2026 - Python
A skill that helps an LLM keep its context lean working within large project repositories, managing its dependencies, tools and data.
Open-source AI agent efficiency platform: LLM-free context filter + early-exit supervisor cuts token costs ~30% with zero accuracy loss. Works with LangChain, AutoGen, CrewAI, LangGraph and Smolagents.
Local MCP tools for document search, reusable document profiles, spreadsheet SQL, JSON snapshot changes, resumable API batches and retry-loop checks. Built by AVRG3.
To associate your repository with the agent-efficiency topic, visit your repo's landing page and select "manage topics."