graphifyy 0.2.2__tar.gz → 0.3.0__tar.gz

graphifyy-0.3.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Safi Shamsi
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{graphifyy-0.2.2 → graphifyy-0.3.0}/PKG-INFO

@@ -1,14 +1,36 @@
 Metadata-Version: 2.4
 Name: graphifyy
-Version: 0.2.2
-Summary: Claude Code skill - turn any folder of code, docs, papers, images, or tweets into a queryable knowledge graph
-License: MIT
+Version: 0.3.0
+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
+        
+        Copyright (c) 2026 Safi Shamsi
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
 Project-URL: Homepage, https://github.com/safishamsi/graphify
 Project-URL: Repository, https://github.com/safishamsi/graphify
 Project-URL: Issues, https://github.com/safishamsi/graphify/issues
-Keywords: claude,claude-code,knowledge-graph,rag,graphrag,obsidian,community-detection,tree-sitter,leiden,llm
+Keywords: claude,claude-code,codex,opencode,knowledge-graph,rag,graphrag,obsidian,community-detection,tree-sitter,leiden,llm
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Requires-Dist: networkx
 Requires-Dist: tree-sitter
 Requires-Dist: tree-sitter-python
@@ -42,13 +64,14 @@ Requires-Dist: pypdf; extra == "all"
 Requires-Dist: html2text; extra == "all"
 Requires-Dist: watchdog; extra == "all"
 Requires-Dist: graspologic; extra == "all"
+Dynamic: license-file
 
 # graphify
 
-[![CI](https://github.com/safishamsi/graphify/actions/workflows/ci.yml/badge.svg?branch=v2)](https://github.com/safishamsi/graphify/actions/workflows/ci.yml)
+[![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/)
 
-**A Claude Code skill.** Type `/graphify` in Claude Code - 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, 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.
 
 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.
 
@@ -82,7 +105,18 @@ pip install graphifyy && graphify install
 
 > The PyPI package is temporarily named `graphifyy` while the `graphify` name is being reclaimed. The CLI and skill command are still `graphify`.
 
-Then open Claude Code in any directory and type:
+### Platform support
+
+| Platform | Install command |
+|----------|----------------|
+| Claude Code | `graphify install` |
+| Codex | `graphify install --platform codex` |
+| OpenCode | `graphify install --platform opencode` |
+| OpenClaw | `graphify install --platform claw` |
+
+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).
+
+Then open your AI coding assistant and type:
 
 ```
 /graphify .
@@ -111,7 +145,7 @@ Uninstall with `graphify claude uninstall`.
 
 ```bash
 mkdir -p ~/.claude/skills/graphify
-curl -fsSL https://raw.githubusercontent.com/safishamsi/graphify/v2/graphify/skill.md \
+curl -fsSL https://raw.githubusercontent.com/safishamsi/graphify/v3/graphify/skill.md \
   > ~/.claude/skills/graphify/SKILL.md
 ```
 
@@ -176,7 +210,7 @@ Works with any mix of file types:
 
 **Hyperedges** - group relationships connecting 3+ nodes that pairwise edges can't express. All classes implementing a shared protocol, all functions in an auth flow, all concepts from a paper section forming one idea.
 
-**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files.
+**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files. The first run extracts and builds the graph (this costs tokens). Every subsequent query reads the compact graph instead of raw files — that's where the savings compound. The SHA256 cache means re-runs only re-process changed files.
 
 **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.
 

{graphifyy-0.2.2 → graphifyy-0.3.0}/README.md

@@ -1,9 +1,9 @@
 # graphify
 
-[![CI](https://github.com/safishamsi/graphify/actions/workflows/ci.yml/badge.svg?branch=v2)](https://github.com/safishamsi/graphify/actions/workflows/ci.yml)
+[![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/)
 
-**A Claude Code skill.** Type `/graphify` in Claude Code - 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, 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.
 
 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.
 
@@ -37,7 +37,18 @@ pip install graphifyy && graphify install
 
 > The PyPI package is temporarily named `graphifyy` while the `graphify` name is being reclaimed. The CLI and skill command are still `graphify`.
 
-Then open Claude Code in any directory and type:
+### Platform support
+
+| Platform | Install command |
+|----------|----------------|
+| Claude Code | `graphify install` |
+| Codex | `graphify install --platform codex` |
+| OpenCode | `graphify install --platform opencode` |
+| OpenClaw | `graphify install --platform claw` |
+
+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).
+
+Then open your AI coding assistant and type:
 
 ```
 /graphify .
@@ -66,7 +77,7 @@ Uninstall with `graphify claude uninstall`.
 
 ```bash
 mkdir -p ~/.claude/skills/graphify
-curl -fsSL https://raw.githubusercontent.com/safishamsi/graphify/v2/graphify/skill.md \
+curl -fsSL https://raw.githubusercontent.com/safishamsi/graphify/v3/graphify/skill.md \
   > ~/.claude/skills/graphify/SKILL.md
 ```
 
@@ -131,7 +142,7 @@ Works with any mix of file types:
 
 **Hyperedges** - group relationships connecting 3+ nodes that pairwise edges can't express. All classes implementing a shared protocol, all functions in an auth flow, all concepts from a paper section forming one idea.
 
-**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files.
+**Token benchmark** - printed automatically after every run. On a mixed corpus (Karpathy repos + papers + images): **71.5x** fewer tokens per query vs reading raw files. The first run extracts and builds the graph (this costs tokens). Every subsequent query reads the compact graph instead of raw files — that's where the savings compound. The SHA256 cache means re-runs only re-process changed files.
 
 **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.
 

{graphifyy-0.2.2 → graphifyy-0.3.0}/graphify/__main__.py

@@ -29,39 +29,66 @@ _SKILL_REGISTRATION = (
 )
 
 
-def _bundled_skill() -> Path:
-    """Path to the skill.md bundled with this package."""
-    return Path(__file__).parent / "skill.md"
+_PLATFORM_CONFIG: dict[str, dict] = {
+    "claude": {
+        "skill_file": "skill.md",
+        "skill_dst": Path(".claude") / "skills" / "graphify" / "SKILL.md",
+        "claude_md": True,
+    },
+    "codex": {
+        "skill_file": "skill-codex.md",
+        "skill_dst": Path(".agents") / "skills" / "graphify" / "SKILL.md",
+        "claude_md": False,
+    },
+    "opencode": {
+        "skill_file": "skill-opencode.md",
+        "skill_dst": Path(".config") / "opencode" / "skills" / "graphify" / "SKILL.md",
+        "claude_md": False,
+    },
+    "claw": {
+        "skill_file": "skill-claw.md",
+        "skill_dst": Path(".claw") / "skills" / "graphify" / "SKILL.md",
+        "claude_md": False,
+    },
+}
+
 
+def install(platform: str = "claude") -> None:
+    if platform not in _PLATFORM_CONFIG:
+        print(
+            f"error: unknown platform '{platform}'. Choose from: {', '.join(_PLATFORM_CONFIG)}",
+            file=sys.stderr,
+        )
+        sys.exit(1)
 
-def install() -> None:
-    skill_src = _bundled_skill()
+    cfg = _PLATFORM_CONFIG[platform]
+    skill_src = Path(__file__).parent / cfg["skill_file"]
     if not skill_src.exists():
-        print("error: skill.md not found in package - reinstall graphify", file=sys.stderr)
+        print(f"error: {cfg['skill_file']} not found in package - reinstall graphify", file=sys.stderr)
         sys.exit(1)
 
-    # Copy skill to ~/.claude/skills/graphify/SKILL.md
-    skill_dst = Path.home() / ".claude" / "skills" / "graphify" / "SKILL.md"
+    skill_dst = Path.home() / cfg["skill_dst"]
     skill_dst.parent.mkdir(parents=True, exist_ok=True)
     shutil.copy(skill_src, skill_dst)
     print(f"  skill installed  →  {skill_dst}")
 
-    # Register in ~/.claude/CLAUDE.md
-    claude_md = Path.home() / ".claude" / "CLAUDE.md"
-    if claude_md.exists():
-        content = claude_md.read_text()
-        if "graphify" in content:
-            print(f"  CLAUDE.md        →  already registered (no change)")
+    if cfg["claude_md"]:
+        # Register in ~/.claude/CLAUDE.md (Claude Code only)
+        claude_md = Path.home() / ".claude" / "CLAUDE.md"
+        if claude_md.exists():
+            content = claude_md.read_text()
+            if "graphify" in content:
+                print(f"  CLAUDE.md        →  already registered (no change)")
+            else:
+                claude_md.write_text(content.rstrip() + _SKILL_REGISTRATION)
+                print(f"  CLAUDE.md        →  skill registered in {claude_md}")
         else:
-            claude_md.write_text(content.rstrip() + _SKILL_REGISTRATION)
-            print(f"  CLAUDE.md        →  skill registered in {claude_md}")
-    else:
-        claude_md.parent.mkdir(parents=True, exist_ok=True)
-        claude_md.write_text(_SKILL_REGISTRATION.lstrip())
-        print(f"  CLAUDE.md        →  created at {claude_md}")
+            claude_md.parent.mkdir(parents=True, exist_ok=True)
+            claude_md.write_text(_SKILL_REGISTRATION.lstrip())
+            print(f"  CLAUDE.md        →  created at {claude_md}")
 
     print()
-    print("Done. Open Claude Code in any directory and type:")
+    print("Done. Open your AI coding assistant and type:")
     print()
     print("  /graphify .")
     print()
@@ -184,7 +211,7 @@ def main() -> None:
         print("Usage: graphify <command>")
         print()
         print("Commands:")
-        print("  install                 copy skill to ~/.claude/skills/ and register in CLAUDE.md")
+        print("  install [--platform P]  copy skill to platform config dir (claude|codex|opencode|claw)")
         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")
@@ -196,7 +223,19 @@ def main() -> None:
 
     cmd = sys.argv[1]
     if cmd == "install":
-        install()
+        platform = "claude"
+        args = sys.argv[2:]
+        i = 0
+        while i < len(args):
+            if args[i].startswith("--platform="):
+                platform = args[i].split("=", 1)[1]
+                i += 1
+            elif args[i] == "--platform" and i + 1 < len(args):
+                platform = args[i + 1]
+                i += 2
+            else:
+                i += 1
+        install(platform=platform)
     elif cmd == "claude":
         subcmd = sys.argv[2] if len(sys.argv) > 2 else ""
         if subcmd == "install":

{graphifyy-0.2.2 → graphifyy-0.3.0}/graphify/build.py

@@ -1,4 +1,25 @@
 # assemble node+edge dicts into a NetworkX graph, preserving edge direction
+#
+# Node deduplication — three layers:
+#
+# 1. Within a file (AST): each extractor tracks a `seen_ids` set. A node ID is
+#    emitted at most once per file, so duplicate class/function definitions in
+#    the same source file are collapsed to the first occurrence.
+#
+# 2. Between files (build): NetworkX G.add_node() is idempotent — calling it
+#    twice with the same ID overwrites the attributes with the second call's
+#    values. Nodes are added in extraction order (AST first, then semantic),
+#    so if the same entity is extracted by both passes the semantic node
+#    silently overwrites the AST node. This is intentional: semantic nodes
+#    carry richer labels and cross-file context, while AST nodes have precise
+#    source_location. If you need to change the priority, reorder extractions
+#    passed to build().
+#
+# 3. Semantic merge (skill): before calling build(), the skill merges cached
+#    and new semantic results using an explicit `seen` set keyed on node["id"],
+#    so duplicates across cache hits and new extractions are resolved there
+#    before any graph construction happens.
+#
 from __future__ import annotations
 import sys
 import networkx as nx
@@ -32,11 +53,18 @@ def build_from_json(extraction: dict) -> nx.Graph:
 
 
 def build(extractions: list[dict]) -> nx.Graph:
-    """Merge multiple extraction results into one graph."""
-    combined: dict = {"nodes": [], "edges": [], "input_tokens": 0, "output_tokens": 0}
+    """Merge multiple extraction results into one graph.
+
+    Extractions are merged in order. For nodes with the same ID, the last
+    extraction's attributes win (NetworkX add_node overwrites). Pass AST
+    results before semantic results so semantic labels take precedence, or
+    reverse the order if you prefer AST source_location precision to win.
+    """
+    combined: dict = {"nodes": [], "edges": [], "hyperedges": [], "input_tokens": 0, "output_tokens": 0}
     for ext in extractions:
         combined["nodes"].extend(ext.get("nodes", []))
         combined["edges"].extend(ext.get("edges", []))
+        combined["hyperedges"].extend(ext.get("hyperedges", []))
         combined["input_tokens"] += ext.get("input_tokens", 0)
         combined["output_tokens"] += ext.get("output_tokens", 0)
     return build_from_json(combined)