Site **graphify.net**, accessed on **August 6, 2026**, maintained by **Safi Shamsi** — the creator of the open source graphify skill (cf. [[skill-shamsi-graphify-2026-08-06]]). The domain carries two distinct objects. **The first is a product showcase**: presentation of graphify, usage guides, CLI reference, and above all a gallery of **100 already-graphified trending GitHub repositories** — *« 100 repos, 854,079 nodes, 1,932,930 edges »* — filterable by language and graph size, each with its preview and detail page. **The second, and the most interesting one for a watch note, is an editorial directory**: *« 30 AI coding client guides »*, a directory of MCP servers compared on *« transport, runtime, client support, setup effort, and access risks »*, structured comparisons between tools (Cursor versus Codex), and a stream of articles with an evidently long-tail targeting (*« GLM-5.2 Knowledge Graph for Developers »*, *« Trae Context Engineering for Agents »*, *« Symphony Knowledge Graph for Agent Memory »*, *« What Is Cowart? A Codex Plugin for Image Editing »*). The site claims a method — *« source-reviewed »*, *« aligned decision fields, official evidence, and explicit unknowns »* — and is available in six languages. ⚠️ **The point this note exists to record**: the site is **factually out of step with the product it presents**. It states **« 3.7k+ GitHub Stars »** when the GitHub API counts **103,187** the same day, an **MIT license** stated three times when the repository's `LICENSE` file is **Apache 2.0**, and highlights the **« 71.5× token reduction »** claim, which belongs to the v1-generation README and has disappeared from the current version. **An official site that shows 3.7% of the actual star count and gets the license wrong** is a signal in itself: the communication layer has not kept pace with the repository.
**Skill** entry (not an article): **graphify** by **Safi Shamsi** (Graphify Labs, **Y Combinator S26**) turns an entire project — code, docs, PDFs, images, videos — into a **queryable knowledge graph**, invoked via `/graphify` from Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, and about fifteen other clients. Observed on **August 6, 2026**: **103,187 stars**, **10,024 forks**, repository created on **April 3, 2026** — an extraordinary trajectory in four months. **Apache-2.0**, Python 3.10+, default branch **v8**. **The three design commitments fit in three lines of the README**: *« Code maps for free, fully local »* (code is parsed into **tree-sitter AST**, deterministic, no LLM, **nothing leaves the machine**); *« Every edge is explained »* (each edge is tagged **`EXTRACTED`** — explicit in the source — or **`INFERRED`** — resolved by graphify —, with a third value `AMBIGUOUS` appearing in the report); and *« Not a vector index »* — *« no embeddings, no vector store: a real graph you traverse »*. **Three outputs**: `graph.html` (interactive graph), `GRAPH_REPORT.md` (god nodes, surprising connections, suggested questions), and `graph.json` (persistent graph, queryable weeks later without re-reading the files). **Three query modes** replace grep: `query` (subgraph for a natural-language question), `path A B` (shortest path between two entities), and `explain` (neighborhood of a concept). **Coverage**: 36 tree-sitter grammars (~40 languages), plus Terraform, Apex, **MCP configurations**, package manifests, Office, Google Workspace, PDFs, images, and video/audio transcribed **locally** by faster-whisper. Communities detected via **Leiden**, labeled **without an LLM**. ⭐ **The most interesting benchmark result is not a win but a free one**: on LOCOMO, graphify achieves a **recall@10 of 0.497** versus 0.149 for supermemory and 0.048 for mem0, but **loses on QA accuracy** (45.3% versus 49.7%); on LongMemEval-S it scores **76%, tied with a dense RAG**; and the line that matters is *« Graph build — LLM credits: **0** »* where the field typically bills per token. ⚠️ **Points to record**: the `main` branch carries a v1-era README describing a different product (Claude Code skill only, the « 71.5× fewer tokens » claim); the PyPI package is named **`graphifyy`** with two *y*'s, until the `graphify` name is reclaimed; and a **query log** is written by default to `~/.cache/graphify-queries.log`, which can be disabled via an environment variable.
#skill#knowledge graph#knowledge graph
**Safi Shamsi** — créateur et mainteneur de graphify · et de **Graphify Labs** · société passée par **Y Combinator (promotion S26)** selon le badge du dépôt. Il maintient aussi le site d'annuaire `graphify.net` (cf. [[graphify-net-annuaire-ia-coding-2026-08-06]]) et publie un livre · *The Memory Layer* · sur les idées et l'architecture derrière le projet.
Empirical study by the **Compare the Market** engineering team (Meerkat Careers, UK) evaluating four approaches to **context retrieval for AI code review**: Baseline (no additional context), **RAG** (vector search), **GKG** (GitLab Knowledge Graph, AST-based knowledge graph), and **GKG+RAG** (hybrid). Evaluation on **79 real merge requests** with **MLflow on Databricks**. Striking result: **RAG performs worse than the baseline** on almost every metric — vector noise is counterproductive for code review. **GKG outperforms RAG by +21%** in inline comments coverage (0.696 vs 0.577) through structural AST understanding (Tree-sitter + Kuzu graph database). Code requires **structural** understanding (callers, signatures, hierarchies), not mere semantic similarity. GKG costs 4× the baseline but delivers measurable improvements; RAG costs 3× with no improvement. Implemented as a **Docker sidecar** in CI/CD wrapping the GKG binary (still in GitLab beta) with a local MCP server.
#Compare the Market#Meerkat Careers#AI code review
Équipe Engineering Compare the Market (Meerkat Careers, UK — site de comparaison d'assurances et services financiers).