graphifyy 0.3.0__tar.gz → 0.3.2__tar.gz

{graphifyy-0.3.0 → graphifyy-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: graphifyy
-Version: 0.3.0
+Version: 0.3.2
 Summary: AI coding assistant skill (Claude Code, Codex, OpenCode, OpenClaw) - turn any folder of code, docs, papers, or images into a queryable knowledge graph
 License: MIT License
         
@@ -46,6 +46,10 @@ Requires-Dist: tree-sitter-c-sharp
 Requires-Dist: tree-sitter-kotlin
 Requires-Dist: tree-sitter-scala
 Requires-Dist: tree-sitter-php
+Requires-Dist: tree-sitter-swift
+Requires-Dist: tree-sitter-lua
+Requires-Dist: tree-sitter-zig
+Requires-Dist: tree-sitter-powershell
 Provides-Extra: mcp
 Requires-Dist: mcp; extra == "mcp"
 Provides-Extra: neo4j
@@ -68,10 +72,12 @@ Dynamic: license-file
 
 # graphify
 
+[English](README.md) | [简体中文](README.zh-CN.md)
+
 [![CI](https://github.com/safishamsi/graphify/actions/workflows/ci.yml/badge.svg?branch=v3)](https://github.com/safishamsi/graphify/actions/workflows/ci.yml)
 [![PyPI](https://img.shields.io/pypi/v/graphifyy)](https://pypi.org/project/graphifyy/)
 
-**An AI coding assistant skill.** Type `/graphify` in Claude Code, Codex, OpenCode, or OpenClaw - it reads your files, builds a knowledge graph, and gives you back structure you didn't know was there. Understand a codebase faster. Find the "why" behind architectural decisions.
+**An AI coding assistant skill.** Type `/graphify` in Claude Code, Codex, OpenCode, OpenClaw, or Factory Droid - it reads your files, builds a knowledge graph, and gives you back structure you didn't know was there. Understand a codebase faster. Find the "why" behind architectural decisions.
 
 Fully multimodal. Drop in code, PDFs, markdown, screenshots, diagrams, whiteboard photos, even images in other languages - graphify uses Claude vision to extract concepts and relationships from all of it and connects them into one graph.
 
@@ -89,15 +95,29 @@ graphify-out/
 └── cache/           SHA256 cache - re-runs only process changed files
 ```
 
+Add a `.graphifyignore` file to exclude folders you don't want in the graph:
+
+```
+# .graphifyignore
+vendor/
+node_modules/
+dist/
+*.generated.py
+```
+
+Same syntax as `.gitignore`. Patterns match against file paths relative to the folder you run graphify on.
+
 ## How it works
 
 graphify runs in two passes. First, a deterministic AST pass extracts structure from code files (classes, functions, imports, call graphs, docstrings, rationale comments) with no LLM needed. Second, Claude subagents run in parallel over docs, papers, and images to extract concepts, relationships, and design rationale. The results are merged into a NetworkX graph, clustered with Leiden community detection, and exported as interactive HTML, queryable JSON, and a plain-language audit report.
 
+**Clustering is graph-topology-based — no embeddings.** Leiden finds communities by edge density. The semantic similarity edges that Claude extracts (`semantically_similar_to`, marked INFERRED) are already in the graph, so they influence community detection directly. The graph structure is the similarity signal — no separate embedding step or vector database needed.
+
 Every relationship is tagged `EXTRACTED` (found directly in source), `INFERRED` (reasonable inference, with a confidence score), or `AMBIGUOUS` (flagged for review). You always know what was found vs guessed.
 
 ## Install
 
-**Requires:** [Claude Code](https://claude.ai/code) and Python 3.10+
+**Requires:** Python 3.10+ and one of: [Claude Code](https://claude.ai/code), [Codex](https://openai.com/codex), [OpenCode](https://opencode.ai), [OpenClaw](https://openclaw.ai), or [Factory Droid](https://factory.ai)
 
 ```bash
 pip install graphifyy && graphify install
@@ -113,8 +133,9 @@ pip install graphifyy && graphify install
 | Codex | `graphify install --platform codex` |
 | OpenCode | `graphify install --platform opencode` |
 | OpenClaw | `graphify install --platform claw` |
+| Factory Droid | `graphify install --platform droid` |
 
-Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. OpenClaw uses sequential extraction (parallel agent support is still early on that platform).
+Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. Factory Droid uses the `Task` tool for parallel subagent dispatch. OpenClaw uses sequential extraction (parallel agent support is still early on that platform).
 
 Then open your AI coding assistant and type:
 
@@ -122,23 +143,31 @@ Then open your AI coding assistant and type:
 /graphify .
 ```
 
-### Make Claude always use the graph (recommended)
+### Make your assistant always use the graph (recommended)
 
 After building a graph, run this once in your project:
 
-```bash
-graphify claude install
-```
+| Platform | Command |
+|----------|---------|
+| Claude Code | `graphify claude install` |
+| Codex | `graphify codex install` |
+| OpenCode | `graphify opencode install` |
+| OpenClaw | `graphify claw install` |
+| Factory Droid | `graphify droid install` |
+
+**Claude Code** does two things: writes a `CLAUDE.md` section telling Claude to read `graphify-out/GRAPH_REPORT.md` before answering architecture questions, and installs a **PreToolUse hook** (`settings.json`) that fires before every Glob and Grep call. If a knowledge graph exists, Claude sees: _"graphify: Knowledge graph exists. Read GRAPH_REPORT.md for god nodes and community structure before searching raw files."_ — so Claude navigates via the graph instead of grepping through every file.
+
+**Codex, OpenCode, OpenClaw, Factory Droid** write the same rules to `AGENTS.md` in your project root. These platforms don't support PreToolUse hooks, so AGENTS.md is the always-on mechanism.
 
-This does two things:
+Uninstall with the matching uninstall command (e.g. `graphify claude uninstall`).
 
-1. **CLAUDE.md rules** - tells Claude to read `graphify-out/GRAPH_REPORT.md` before answering architecture questions, and to rebuild the graph after editing code files.
+**Always-on vs explicit trigger — what's the difference?**
 
-2. **PreToolUse hook** (`settings.json`) - fires automatically before every Glob and Grep call. If a knowledge graph exists, Claude sees: _"graphify: Knowledge graph exists. Read GRAPH_REPORT.md for god nodes and community structure before searching raw files."_ This means Claude navigates via the graph instead of grepping through every file - faster answers, fewer wasted tool calls, and responses grounded in the actual structure of your codebase rather than keyword matches.
+The always-on hook surfaces `GRAPH_REPORT.md` — a one-page summary of god nodes, communities, and surprising connections. Your assistant reads this before searching files, so it navigates by structure instead of keyword matching. That covers most everyday questions.
 
-Without this, Claude will grep raw files by default even when a graph exists. With it, the graph becomes the first thing Claude reaches for.
+`/graphify query`, `/graphify path`, and `/graphify explain` go deeper: they traverse the raw `graph.json` hop by hop, trace exact paths between nodes, and surface edge-level detail (relation type, confidence score, source location). Use them when you want a specific question answered from the graph rather than a general orientation.
 
-Uninstall with `graphify claude uninstall`.
+Think of it this way: the always-on hook gives your assistant a map. The `/graphify` commands let it navigate the map precisely.
 
 <details>
 <summary>Manual install (curl)</summary>
@@ -165,12 +194,18 @@ When the user types `/graphify`, invoke the Skill tool with `skill: "graphify"`
 /graphify ./raw                    # run on a specific folder
 /graphify ./raw --mode deep        # more aggressive INFERRED edge extraction
 /graphify ./raw --update           # re-extract only changed files, merge into existing graph
+/graphify ./raw --cluster-only     # rerun clustering on existing graph, no re-extraction
+/graphify ./raw --no-viz           # skip HTML, just produce report + JSON
 /graphify ./raw --obsidian         # also generate Obsidian vault (opt-in)
 
 /graphify add https://arxiv.org/abs/1706.03762        # fetch a paper, save, update graph
 /graphify add https://x.com/karpathy/status/...       # fetch a tweet
+/graphify add https://... --author "Name"             # tag the original author
+/graphify add https://... --contributor "Name"        # tag who added it to the corpus
 
 /graphify query "what connects attention to the optimizer?"
+/graphify query "what connects attention to the optimizer?" --dfs   # trace a specific path
+/graphify query "what connects attention to the optimizer?" --budget 1500  # cap at N tokens
 /graphify path "DigestAuth" "Response"
 /graphify explain "SwinTransformer"
 
@@ -179,17 +214,28 @@ When the user types `/graphify`, invoke the Skill tool with `skill: "graphify"`
 /graphify ./raw --svg              # export graph.svg
 /graphify ./raw --graphml          # export graph.graphml (Gephi, yEd)
 /graphify ./raw --neo4j            # generate cypher.txt for Neo4j
+/graphify ./raw --neo4j-push bolt://localhost:7687    # push directly to a running Neo4j instance
 /graphify ./raw --mcp              # start MCP stdio server
 
-graphify hook install              # git hooks - rebuilds graph on commit and branch switch
-graphify claude install            # always-on: CLAUDE.md + PreToolUse hook for this project
+# git hooks - platform-agnostic, rebuild graph on commit and branch switch
+graphify hook install
+graphify hook uninstall
+graphify hook status
+
+# always-on assistant instructions - platform-specific
+graphify claude install            # CLAUDE.md + PreToolUse hook (Claude Code)
+graphify claude uninstall
+graphify codex install             # AGENTS.md (Codex)
+graphify opencode install          # AGENTS.md (OpenCode)
+graphify claw install              # AGENTS.md (OpenClaw)
+graphify droid install             # AGENTS.md (Factory Droid)
 ```
 
 Works with any mix of file types:
 
 | Type | Extensions | Extraction |
 |------|-----------|------------|
-| Code | `.py .ts .js .go .rs .java .c .cpp .rb .cs .kt .scala .php` | AST via tree-sitter + call-graph + docstring/comment rationale |
+| Code | `.py .ts .js .go .rs .java .c .cpp .rb .cs .kt .scala .php .swift .lua .zig .ps1` | AST via tree-sitter + call-graph + docstring/comment rationale |
 | Docs | `.md .txt .rst` | Concepts + relationships + design rationale via Claude |
 | Papers | `.pdf` | Citation mining + concept extraction |
 | Images | `.png .jpg .webp .gif` | Claude vision - screenshots, diagrams, any language |
@@ -214,7 +260,7 @@ Works with any mix of file types:
 
 **Auto-sync** (`--watch`) - run in a background terminal and the graph updates itself as your codebase changes. Code file saves trigger an instant rebuild (AST only, no LLM). Doc/image changes notify you to run `--update` for the LLM re-pass.
 
-**Git hooks** (`graphify hook install`) - installs post-commit and post-checkout hooks. Graph rebuilds automatically after every commit and every branch switch. No background process needed.
+**Git hooks** (`graphify hook install`) - installs post-commit and post-checkout hooks. Graph rebuilds automatically after every commit and every branch switch. If a rebuild fails, the hook exits with a non-zero code so git surfaces the error instead of silently continuing. No background process needed.
 
 **Wiki** (`--wiki`) - Wikipedia-style markdown articles per community and god node, with an `index.md` entry point. Point any agent at `index.md` and it can navigate the knowledge base by reading files instead of parsing JSON.
 
@@ -230,11 +276,11 @@ Token reduction scales with corpus size. 6 files fits in a context window anyway
 
 ## Privacy
 
-graphify sends file contents to the Claude API (Anthropic) for semantic extraction of docs, papers, and images. Code files are processed locally via tree-sitter AST — no file contents leave your machine for code. No telemetry, usage tracking, or analytics of any kind. The only network calls are to Anthropic's API during extraction, using your own API key via Claude Code.
+graphify sends file contents to your AI coding assistant's underlying model API for semantic extraction of docs, papers, and images — Anthropic (Claude Code), OpenAI (Codex), or whichever provider your platform uses. Code files are processed locally via tree-sitter AST — no file contents leave your machine for code. No telemetry, usage tracking, or analytics of any kind. The only network calls are to your platform's model API during extraction, using your own API key.
 
 ## Tech stack
 
-NetworkX + Leiden (graspologic) + tree-sitter + Claude + vis.js. No Neo4j required, no server, runs entirely locally.
+NetworkX + Leiden (graspologic) + tree-sitter + vis.js. Semantic extraction via Claude (Claude Code), GPT-4 (Codex), or whichever model your platform runs. No Neo4j required, no server, runs entirely locally.
 
 <details>
 <summary>Contributing</summary>

{graphifyy-0.3.0 → graphifyy-0.3.2}/README.md

@@ -1,9 +1,11 @@
 # graphify
 
+[English](README.md) | [简体中文](README.zh-CN.md)
+
 [![CI](https://github.com/safishamsi/graphify/actions/workflows/ci.yml/badge.svg?branch=v3)](https://github.com/safishamsi/graphify/actions/workflows/ci.yml)
 [![PyPI](https://img.shields.io/pypi/v/graphifyy)](https://pypi.org/project/graphifyy/)
 
-**An AI coding assistant skill.** Type `/graphify` in Claude Code, Codex, OpenCode, or OpenClaw - it reads your files, builds a knowledge graph, and gives you back structure you didn't know was there. Understand a codebase faster. Find the "why" behind architectural decisions.
+**An AI coding assistant skill.** Type `/graphify` in Claude Code, Codex, OpenCode, OpenClaw, or Factory Droid - it reads your files, builds a knowledge graph, and gives you back structure you didn't know was there. Understand a codebase faster. Find the "why" behind architectural decisions.
 
 Fully multimodal. Drop in code, PDFs, markdown, screenshots, diagrams, whiteboard photos, even images in other languages - graphify uses Claude vision to extract concepts and relationships from all of it and connects them into one graph.
 
@@ -21,15 +23,29 @@ graphify-out/
 └── cache/           SHA256 cache - re-runs only process changed files
 ```
 
+Add a `.graphifyignore` file to exclude folders you don't want in the graph:
+
+```
+# .graphifyignore
+vendor/
+node_modules/
+dist/
+*.generated.py
+```
+
+Same syntax as `.gitignore`. Patterns match against file paths relative to the folder you run graphify on.
+
 ## How it works
 
 graphify runs in two passes. First, a deterministic AST pass extracts structure from code files (classes, functions, imports, call graphs, docstrings, rationale comments) with no LLM needed. Second, Claude subagents run in parallel over docs, papers, and images to extract concepts, relationships, and design rationale. The results are merged into a NetworkX graph, clustered with Leiden community detection, and exported as interactive HTML, queryable JSON, and a plain-language audit report.
 
+**Clustering is graph-topology-based — no embeddings.** Leiden finds communities by edge density. The semantic similarity edges that Claude extracts (`semantically_similar_to`, marked INFERRED) are already in the graph, so they influence community detection directly. The graph structure is the similarity signal — no separate embedding step or vector database needed.
+
 Every relationship is tagged `EXTRACTED` (found directly in source), `INFERRED` (reasonable inference, with a confidence score), or `AMBIGUOUS` (flagged for review). You always know what was found vs guessed.
 
 ## Install
 
-**Requires:** [Claude Code](https://claude.ai/code) and Python 3.10+
+**Requires:** Python 3.10+ and one of: [Claude Code](https://claude.ai/code), [Codex](https://openai.com/codex), [OpenCode](https://opencode.ai), [OpenClaw](https://openclaw.ai), or [Factory Droid](https://factory.ai)
 
 ```bash
 pip install graphifyy && graphify install
@@ -45,8 +61,9 @@ pip install graphifyy && graphify install
 | Codex | `graphify install --platform codex` |
 | OpenCode | `graphify install --platform opencode` |
 | OpenClaw | `graphify install --platform claw` |
+| Factory Droid | `graphify install --platform droid` |
 
-Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. OpenClaw uses sequential extraction (parallel agent support is still early on that platform).
+Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. Factory Droid uses the `Task` tool for parallel subagent dispatch. OpenClaw uses sequential extraction (parallel agent support is still early on that platform).
 
 Then open your AI coding assistant and type:
 
@@ -54,23 +71,31 @@ Then open your AI coding assistant and type:
 /graphify .
 ```
 
-### Make Claude always use the graph (recommended)
+### Make your assistant always use the graph (recommended)
 
 After building a graph, run this once in your project:
 
-```bash
-graphify claude install
-```
+| Platform | Command |
+|----------|---------|
+| Claude Code | `graphify claude install` |
+| Codex | `graphify codex install` |
+| OpenCode | `graphify opencode install` |
+| OpenClaw | `graphify claw install` |
+| Factory Droid | `graphify droid install` |
+
+**Claude Code** does two things: writes a `CLAUDE.md` section telling Claude to read `graphify-out/GRAPH_REPORT.md` before answering architecture questions, and installs a **PreToolUse hook** (`settings.json`) that fires before every Glob and Grep call. If a knowledge graph exists, Claude sees: _"graphify: Knowledge graph exists. Read GRAPH_REPORT.md for god nodes and community structure before searching raw files."_ — so Claude navigates via the graph instead of grepping through every file.
+
+**Codex, OpenCode, OpenClaw, Factory Droid** write the same rules to `AGENTS.md` in your project root. These platforms don't support PreToolUse hooks, so AGENTS.md is the always-on mechanism.
 
-This does two things:
+Uninstall with the matching uninstall command (e.g. `graphify claude uninstall`).
 
-1. **CLAUDE.md rules** - tells Claude to read `graphify-out/GRAPH_REPORT.md` before answering architecture questions, and to rebuild the graph after editing code files.
+**Always-on vs explicit trigger — what's the difference?**
 
-2. **PreToolUse hook** (`settings.json`) - fires automatically before every Glob and Grep call. If a knowledge graph exists, Claude sees: _"graphify: Knowledge graph exists. Read GRAPH_REPORT.md for god nodes and community structure before searching raw files."_ This means Claude navigates via the graph instead of grepping through every file - faster answers, fewer wasted tool calls, and responses grounded in the actual structure of your codebase rather than keyword matches.
+The always-on hook surfaces `GRAPH_REPORT.md` — a one-page summary of god nodes, communities, and surprising connections. Your assistant reads this before searching files, so it navigates by structure instead of keyword matching. That covers most everyday questions.
 
-Without this, Claude will grep raw files by default even when a graph exists. With it, the graph becomes the first thing Claude reaches for.
+`/graphify query`, `/graphify path`, and `/graphify explain` go deeper: they traverse the raw `graph.json` hop by hop, trace exact paths between nodes, and surface edge-level detail (relation type, confidence score, source location). Use them when you want a specific question answered from the graph rather than a general orientation.
 
-Uninstall with `graphify claude uninstall`.
+Think of it this way: the always-on hook gives your assistant a map. The `/graphify` commands let it navigate the map precisely.
 
 <details>
 <summary>Manual install (curl)</summary>
@@ -97,12 +122,18 @@ When the user types `/graphify`, invoke the Skill tool with `skill: "graphify"`
 /graphify ./raw                    # run on a specific folder
 /graphify ./raw --mode deep        # more aggressive INFERRED edge extraction
 /graphify ./raw --update           # re-extract only changed files, merge into existing graph
+/graphify ./raw --cluster-only     # rerun clustering on existing graph, no re-extraction
+/graphify ./raw --no-viz           # skip HTML, just produce report + JSON
 /graphify ./raw --obsidian         # also generate Obsidian vault (opt-in)
 
 /graphify add https://arxiv.org/abs/1706.03762        # fetch a paper, save, update graph
 /graphify add https://x.com/karpathy/status/...       # fetch a tweet
+/graphify add https://... --author "Name"             # tag the original author
+/graphify add https://... --contributor "Name"        # tag who added it to the corpus
 
 /graphify query "what connects attention to the optimizer?"
+/graphify query "what connects attention to the optimizer?" --dfs   # trace a specific path
+/graphify query "what connects attention to the optimizer?" --budget 1500  # cap at N tokens
 /graphify path "DigestAuth" "Response"
 /graphify explain "SwinTransformer"
 
@@ -111,17 +142,28 @@ When the user types `/graphify`, invoke the Skill tool with `skill: "graphify"`
 /graphify ./raw --svg              # export graph.svg
 /graphify ./raw --graphml          # export graph.graphml (Gephi, yEd)
 /graphify ./raw --neo4j            # generate cypher.txt for Neo4j
+/graphify ./raw --neo4j-push bolt://localhost:7687    # push directly to a running Neo4j instance
 /graphify ./raw --mcp              # start MCP stdio server
 
-graphify hook install              # git hooks - rebuilds graph on commit and branch switch
-graphify claude install            # always-on: CLAUDE.md + PreToolUse hook for this project
+# git hooks - platform-agnostic, rebuild graph on commit and branch switch
+graphify hook install
+graphify hook uninstall
+graphify hook status
+
+# always-on assistant instructions - platform-specific
+graphify claude install            # CLAUDE.md + PreToolUse hook (Claude Code)
+graphify claude uninstall
+graphify codex install             # AGENTS.md (Codex)
+graphify opencode install          # AGENTS.md (OpenCode)
+graphify claw install              # AGENTS.md (OpenClaw)
+graphify droid install             # AGENTS.md (Factory Droid)
 ```
 
 Works with any mix of file types:
 
 | Type | Extensions | Extraction |
 |------|-----------|------------|
-| Code | `.py .ts .js .go .rs .java .c .cpp .rb .cs .kt .scala .php` | AST via tree-sitter + call-graph + docstring/comment rationale |
+| Code | `.py .ts .js .go .rs .java .c .cpp .rb .cs .kt .scala .php .swift .lua .zig .ps1` | AST via tree-sitter + call-graph + docstring/comment rationale |
 | Docs | `.md .txt .rst` | Concepts + relationships + design rationale via Claude |
 | Papers | `.pdf` | Citation mining + concept extraction |
 | Images | `.png .jpg .webp .gif` | Claude vision - screenshots, diagrams, any language |
@@ -146,7 +188,7 @@ Works with any mix of file types:
 
 **Auto-sync** (`--watch`) - run in a background terminal and the graph updates itself as your codebase changes. Code file saves trigger an instant rebuild (AST only, no LLM). Doc/image changes notify you to run `--update` for the LLM re-pass.
 
-**Git hooks** (`graphify hook install`) - installs post-commit and post-checkout hooks. Graph rebuilds automatically after every commit and every branch switch. No background process needed.
+**Git hooks** (`graphify hook install`) - installs post-commit and post-checkout hooks. Graph rebuilds automatically after every commit and every branch switch. If a rebuild fails, the hook exits with a non-zero code so git surfaces the error instead of silently continuing. No background process needed.
 
 **Wiki** (`--wiki`) - Wikipedia-style markdown articles per community and god node, with an `index.md` entry point. Point any agent at `index.md` and it can navigate the knowledge base by reading files instead of parsing JSON.
 
@@ -162,11 +204,11 @@ Token reduction scales with corpus size. 6 files fits in a context window anyway
 
 ## Privacy
 
-graphify sends file contents to the Claude API (Anthropic) for semantic extraction of docs, papers, and images. Code files are processed locally via tree-sitter AST — no file contents leave your machine for code. No telemetry, usage tracking, or analytics of any kind. The only network calls are to Anthropic's API during extraction, using your own API key via Claude Code.
+graphify sends file contents to your AI coding assistant's underlying model API for semantic extraction of docs, papers, and images — Anthropic (Claude Code), OpenAI (Codex), or whichever provider your platform uses. Code files are processed locally via tree-sitter AST — no file contents leave your machine for code. No telemetry, usage tracking, or analytics of any kind. The only network calls are to your platform's model API during extraction, using your own API key.
 
 ## Tech stack
 
-NetworkX + Leiden (graspologic) + tree-sitter + Claude + vis.js. No Neo4j required, no server, runs entirely locally.
+NetworkX + Leiden (graspologic) + tree-sitter + vis.js. Semantic extraction via Claude (Claude Code), GPT-4 (Codex), or whichever model your platform runs. No Neo4j required, no server, runs entirely locally.
 
 <details>
 <summary>Contributing</summary>

{graphifyy-0.3.0 → graphifyy-0.3.2}/graphify/__main__.py

@@ -50,6 +50,11 @@ _PLATFORM_CONFIG: dict[str, dict] = {
         "skill_dst": Path(".claw") / "skills" / "graphify" / "SKILL.md",
         "claude_md": False,
     },
+    "droid": {
+        "skill_file": "skill-droid.md",
+        "skill_dst": Path(".factory") / "skills" / "graphify" / "SKILL.md",
+        "claude_md": False,
+    },
 }
 
 
@@ -107,6 +112,71 @@ Rules:
 
 _CLAUDE_MD_MARKER = "## graphify"
 
+# AGENTS.md section for Codex, OpenCode, and OpenClaw.
+# All three platforms read AGENTS.md in the project root for persistent instructions.
+_AGENTS_MD_SECTION = """\
+## graphify
+
+This project has a graphify knowledge graph at graphify-out/.
+
+Rules:
+- Before answering architecture or codebase questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure
+- If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
+- After modifying code files in this session, run `python3 -c "from graphify.watch import _rebuild_code; from pathlib import Path; _rebuild_code(Path('.'))"` to keep the graph current
+"""
+
+_AGENTS_MD_MARKER = "## graphify"
+
+
+def _agents_install(project_dir: Path, platform: str) -> None:
+    """Write the graphify section to the local AGENTS.md (Codex/OpenCode/OpenClaw)."""
+    target = (project_dir or Path(".")) / "AGENTS.md"
+
+    if target.exists():
+        content = target.read_text()
+        if _AGENTS_MD_MARKER in content:
+            print(f"graphify already configured in AGENTS.md")
+            return
+        new_content = content.rstrip() + "\n\n" + _AGENTS_MD_SECTION
+    else:
+        new_content = _AGENTS_MD_SECTION
+
+    target.write_text(new_content)
+    print(f"graphify section written to {target.resolve()}")
+    print()
+    print(f"{platform.capitalize()} will now check the knowledge graph before answering")
+    print("codebase questions and rebuild it after code changes.")
+    print()
+    print("Note: unlike Claude Code, there is no PreToolUse hook equivalent for")
+    print(f"{platform.capitalize()} — the AGENTS.md rules are the always-on mechanism.")
+
+
+def _agents_uninstall(project_dir: Path) -> None:
+    """Remove the graphify section from the local AGENTS.md."""
+    target = (project_dir or Path(".")) / "AGENTS.md"
+
+    if not target.exists():
+        print("No AGENTS.md found in current directory - nothing to do")
+        return
+
+    content = target.read_text()
+    if _AGENTS_MD_MARKER not in content:
+        print("graphify section not found in AGENTS.md - nothing to do")
+        return
+
+    cleaned = re.sub(
+        r"\n*## graphify\n.*?(?=\n## |\Z)",
+        "",
+        content,
+        flags=re.DOTALL,
+    ).rstrip()
+    if cleaned:
+        target.write_text(cleaned + "\n")
+        print(f"graphify section removed from {target.resolve()}")
+    else:
+        target.unlink()
+        print(f"AGENTS.md was empty after removal - deleted {target.resolve()}")
+
 
 def claude_install(project_dir: Path | None = None) -> None:
     """Write the graphify section to the local CLAUDE.md."""
@@ -211,13 +281,21 @@ def main() -> None:
         print("Usage: graphify <command>")
         print()
         print("Commands:")
-        print("  install [--platform P]  copy skill to platform config dir (claude|codex|opencode|claw)")
+        print("  install [--platform P]  copy skill to platform config dir (claude|codex|opencode|claw|droid)")
         print("  benchmark [graph.json]  measure token reduction vs naive full-corpus approach")
-        print("  hook install            install post-commit git hook (auto-rebuilds graph on commit)")
-        print("  hook uninstall          remove post-commit git hook")
-        print("  hook status             check if hook is installed")
-        print("  claude install          write graphify section to local CLAUDE.md")
-        print("  claude uninstall        remove graphify section from local CLAUDE.md")
+        print("  hook install            install post-commit/post-checkout git hooks (all platforms)")
+        print("  hook uninstall          remove git hooks")
+        print("  hook status             check if git hooks are installed")
+        print("  claude install          write graphify section to CLAUDE.md + PreToolUse hook (Claude Code)")
+        print("  claude uninstall        remove graphify section from CLAUDE.md + PreToolUse hook")
+        print("  codex install           write graphify section to AGENTS.md (Codex)")
+        print("  codex uninstall         remove graphify section from AGENTS.md")
+        print("  opencode install        write graphify section to AGENTS.md (OpenCode)")
+        print("  opencode uninstall      remove graphify section from AGENTS.md")
+        print("  claw install            write graphify section to AGENTS.md (OpenClaw)")
+        print("  claw uninstall          remove graphify section from AGENTS.md")
+        print("  droid install           write graphify section to AGENTS.md (Factory Droid)")
+        print("  droid uninstall         remove graphify section from AGENTS.md")
         print()
         return
 
@@ -245,6 +323,15 @@ def main() -> None:
         else:
             print("Usage: graphify claude [install|uninstall]", file=sys.stderr)
             sys.exit(1)
+    elif cmd in ("codex", "opencode", "claw", "droid"):
+        subcmd = sys.argv[2] if len(sys.argv) > 2 else ""
+        if subcmd == "install":
+            _agents_install(Path("."), cmd)
+        elif subcmd == "uninstall":
+            _agents_uninstall(Path("."))
+        else:
+            print(f"Usage: graphify {cmd} [install|uninstall]", file=sys.stderr)
+            sys.exit(1)
     elif cmd == "hook":
         from graphify.hooks import install as hook_install, uninstall as hook_uninstall, status as hook_status
         subcmd = sys.argv[2] if len(sys.argv) > 2 else ""

{graphifyy-0.3.0 → graphifyy-0.3.2}/graphify/analyze.py

@@ -16,12 +16,16 @@ def _is_file_node(G: nx.Graph, node_id: str) -> bool:
     These are synthetic nodes created by the AST extractor and should be excluded
     from god nodes, surprising connections, and knowledge gap reporting.
     """
-    label = G.nodes[node_id].get("label", "")
+    attrs = G.nodes[node_id]
+    label = attrs.get("label", "")
     if not label:
         return False
-    # File-level hub: label is a filename with a code extension
-    if label.split(".")[-1] in ("py", "ts", "js", "go", "rs", "java", "rb", "cpp", "c", "h"):
-        return True
+    # File-level hub: label matches the actual source filename (not just any label ending in .py)
+    source_file = attrs.get("source_file", "")
+    if source_file:
+        from pathlib import Path as _Path
+        if label == _Path(source_file).name:
+            return True
     # Method stub: AST extractor labels methods as '.method_name()'
     if label.startswith(".") and label.endswith("()"):
         return True
@@ -468,7 +472,7 @@ def graph_diff(G_old: nx.Graph, G_new: nx.Graph) -> dict:
     ]
 
     def edge_key(G: nx.Graph, u: str, v: str, data: dict) -> tuple:
-        return (u, v, data.get("relation", ""))
+        return (min(u, v), max(u, v), data.get("relation", ""))
 
     old_edge_keys = {
         edge_key(G_old, u, v, d)

{graphifyy-0.3.0 → graphifyy-0.3.2}/graphify/cache.py

@@ -3,12 +3,18 @@ from __future__ import annotations
 
 import hashlib
 import json
+import os
 from pathlib import Path
 
 
 def file_hash(path: Path) -> str:
-    """SHA256 of file contents, hex digest."""
-    return hashlib.sha256(Path(path).read_bytes()).hexdigest()
+    """SHA256 of file contents + resolved path. Prevents cache collisions on identical content."""
+    p = Path(path)
+    h = hashlib.sha256()
+    h.update(p.read_bytes())
+    h.update(b"\x00")
+    h.update(str(p.resolve()).encode())
+    return h.hexdigest()
 
 
 def cache_dir(root: Path = Path(".")) -> Path:
@@ -46,7 +52,13 @@ def save_cached(path: Path, result: dict, root: Path = Path(".")) -> None:
     """
     h = file_hash(path)
     entry = cache_dir(root) / f"{h}.json"
-    entry.write_text(json.dumps(result))
+    tmp = entry.with_suffix(".tmp")
+    try:
+        tmp.write_text(json.dumps(result))
+        os.replace(tmp, entry)
+    except Exception:
+        tmp.unlink(missing_ok=True)
+        raise
 
 
 def cached_files(root: Path = Path(".")) -> set[str]: