CTX: CTX is a local context runtime for OpenCode and AI coding agents. It reduces token waste by indexing repositories, storing reusable guidance as graph memory, and providing compact task packs, read-cache compression, command pruning, and a live right-sidebar dashboard. It integrates natively with OpenCode as a context layer without replacing the agent launcher.; context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.
Reducing token costs in OpenCode and AI coding workflows
Deep repository research and analysis (e.g., architecture, contributors, issues)