Houssem BEN ABDALLAH: “Yes, in the README: the same agent with and without phpgraph…”

Houssem BEN ABDALLAH @hbenabdallahOct 1715a0267

Pointed phpgraph at /dev/null's own code. 531 files parsed, 0 failed. 1,835 nodes, 6,640 edges. Routes, controllers, actions, jobs and models, all linked. Static analysis, no LLM, no guessing it doesn't admit to: every edge says if it was EXTRACTED from the code, INFERRED from…

GitHubGitHub - hbenabdallah/phpgraph: Knowledge graph of PHP codebases for AI coding agents (Claude Code, Codex, Cursor) over MCP. Static analysis, no LLM.Knowledge graph of PHP codebases for AI coding agents (Claude Code, Codex, Cursor) over MCP. Static analysis, no LLM. - hbenabdallah/phpgraph

Nehal Hasnayeen @HasnayeenOct 17feb6054

is there a benchmark or test of how much token is saved when agent used phpgraph instead of grep?

Houssem BEN ABDALLAH @hbenabdallahOct 17

Yes, in the README: the same agent with and without phpgraph on a 4,800-file Symfony/DDD project, 3 runs each. Impact questions: -42% tokens, -59% tool calls. Explaining a feature: -25% tokens, -49% tool calls. Same answer quality or better. github.com/hbenabdallah/phpgraph#with-an-agent

14:50 · Oct 17, 2026commit ce8970c

Commit