@ttsc/graph, an MCP server that provides AI agents with a code graph instead of source files, reduces AI token usage by about 90% by eliminating the need for agents to read file bodies. The tool index…
A developer built @ttsc/graph, an MCP tool that provides coding agents with a TypeScript compiler-built code graph instead of raw source files. In benchmarks, it reduces token usage by roughly 10x on …
A developer measured the token cost of context provisioning for AI coding agents across 936 runs on the Apache Superset repository, comparing grep, graph-based, and LSP-based approaches. The results s…
A developer cut token usage by 82% across over 6,000 commands, saving 7.4 million tokens, by trimming the CLAUDE.md rules file, using automatic compression plugins (RTK, claude-mem, codegraph), and ti…