graphora-kg 0.2.0__tar.gz

graphora_kg-0.2.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

graphora_kg-0.2.0/PKG-INFO

@@ -0,0 +1,258 @@
+Metadata-Version: 2.4
+Name: graphora-kg
+Version: 0.2.0
+Summary: Deterministic code knowledge graph: index with tree-sitter, query blast radius, mine risk memory from git, review diffs grounded in structure. No LLM required to build.
+Author: Naseem77
+License: MIT
+Project-URL: Homepage, https://github.com/Naseem77/Graphora
+Project-URL: Repository, https://github.com/Naseem77/Graphora
+Project-URL: Issues, https://github.com/Naseem77/Graphora/issues
+Keywords: knowledge-graph,code-review,falkordb,tree-sitter,blast-radius,mcp
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: falkordb>=1.0
+Requires-Dist: tree-sitter>=0.23
+Requires-Dist: tree-sitter-python>=0.23
+Requires-Dist: tree-sitter-javascript>=0.23
+Requires-Dist: tree-sitter-typescript>=0.23
+Requires-Dist: tree-sitter-go>=0.23
+Requires-Dist: tree-sitter-java>=0.23
+Requires-Dist: tree-sitter-rust>=0.23
+Requires-Dist: tree-sitter-c>=0.23
+Requires-Dist: tree-sitter-cpp>=0.23
+Requires-Dist: tree-sitter-ruby>=0.23
+Requires-Dist: tree-sitter-php>=0.23
+Provides-Extra: llm
+Requires-Dist: litellm>=1.40; extra == "llm"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0; extra == "mcp"
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Dynamic: license-file
+
+<div align="center">
+
+# Graphora
+
+### The code knowledge graph that reviews your changes.
+
+**Deterministic indexing · Blast-radius analysis · Risk memory · Zero Docker required · $0 LLM cost to build**
+
+[![Python](https://img.shields.io/badge/Python-3.10%2B-3776AB?logo=python&logoColor=white)](https://www.python.org/)
+[![FalkorDB](https://img.shields.io/badge/FalkorDB-graph-FF4438?logo=redis&logoColor=white)](https://www.falkordb.com/)
+[![tree--sitter](https://img.shields.io/badge/tree--sitter-parsing-2C2C2C)](https://tree-sitter.github.io/tree-sitter/)
+[![MCP](https://img.shields.io/badge/MCP-server-6E56CF)](https://modelcontextprotocol.io/)
+[![Tests](https://img.shields.io/badge/tests-80%20passing-brightgreen)](#testing)
+[![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
+
+<img src="assets/banner.gif" alt="Graphora: source files flow into a live knowledge graph that powers blast radius, diff review with risk memory, and MCP tools for agents. 22,160 repo tokens shrink to 1,237." width="900" />
+
+`pip install` it as a library · run it as a CLI · plug it into any AI agent as an MCP server · or install the skill into 22 agents with one command
+
+</div>
+
+---
+
+> **TL;DR**: Graphora keeps a live structural graph of your codebase, built with tree-sitter and zero LLM calls, stored in FalkorDB or in a zero-setup embedded backend. When code changes, it reads the real blast radius (callers, callees, tests, importers) straight from the graph, remembers where the codebase broke before (risk memory mined from git history), and grounds every review claim in tagged, auditable facts. Measured result: **82 to 94% fewer prompt tokens** than repo dumping on real pinned OSS repos, with *more* accurate reviews.
+
+## Why Graphora
+
+AI code review and AI coding agents share the same blind spot: they see text, not structure.
+
+| Problem | What goes wrong |
+| --- | --- |
+| **Blind to blast radius** | A one-line change to a shared function looks harmless in isolation. Its callers, tests, and dependents live in other files, outside the diff. |
+| **Expensive to compensate** | The usual fix is stuffing more of the repo into the prompt. That burns tokens and still buries the signal in noise. |
+| **Hard to trust** | Without grounding, the model guesses. Reviewers cannot tell a grounded claim from a hallucination. |
+| **No memory of pain** | Every review starts from zero. The tool does not know that this exact function was hotfixed twice and reverted once. |
+
+Graphora fixes all four at the source:
+
+| Capability | How |
+| --- | --- |
+| **Live structural graph** | `File`, `Function`, `Class`, `Module` nodes; `CALLS`, `DEFINED_IN`, `IMPORTS` edges. Built deterministically with tree-sitter, updated incrementally. |
+| **Blast radius, not repo dumps** | Pure Cypher queries return exactly the callers, callees, covering tests, and importers of a change. Hundreds of tokens instead of tens of thousands. |
+| **Confidence tags on every fact** | `EXTRACTED` (explicit in source), `INFERRED` (single-candidate name resolution), `AMBIGUOUS` (multiple candidates, all linked and flagged). You always know what was read versus guessed. |
+| **Risk memory** | Git history mining links fix, hotfix, and revert commits to the exact symbols they touched. Each symbol carries `fix_count`, `last_broke_at`, and a `risk_score` that decays as the area stays quiet. Reviews warn on historically fragile code automatically. |
+| **Zero-setup or client-server** | Works instantly with an embedded pure-Python backend (JSON on disk, no Docker), or against a shared FalkorDB server for live Cypher and multi-project teams. Auto-detected. |
+| **11 languages** | Python, JavaScript, TypeScript (+JSX/TSX), Go, Java, Rust, C, C++, Ruby, PHP. Tree-sitter first, regex fallback. |
+| **$0 index cost** | No LLM, no embeddings, no network in the index path. Code never leaves your machine unless *you* enable the optional LLM review pass. |
+
+## Quick start
+
+```bash
+# 1. Install (no server, no Docker needed)
+pip install graphora-kg     # from PyPI, or: pip install -e . inside this repo
+
+# 2. Build the graph and the risk memory (both offline, both $0)
+graphora index /path/to/repo
+graphora risk mine /path/to/repo
+
+# 3. Use it
+graphora blast my_function                 # who calls it, who tests it, did it break before
+graphora risk top                          # the riskiest symbols in the codebase
+graphora review --git-range main...HEAD --repo /path/to/repo
+graphora benchmark /path/to/repo           # reproduce the token-cost numbers yourself
+```
+
+Zero configuration: without a FalkorDB server Graphora uses its embedded backend (pure Python, JSON at `~/.graphora`). For live Cypher queries and team-shared graphs, start FalkorDB and Graphora picks it up automatically:
+
+```bash
+docker run -d --name graphora-falkordb -p 6379:6379 falkordb/falkordb:latest
+# force a backend anytime with --backend embedded|falkordb|auto
+```
+
+## Four ways to consume it
+
+### 1. CLI
+
+```text
+graphora index PATH                 Build the graph for a repository (no LLM)
+graphora blast SYMBOL [...]         Blast radius: callers, callees, tests, risk
+graphora review [--diff F|--git-range R]   Grounded diff review (LLM optional via --llm)
+graphora risk mine PATH             Mine git fix/revert history into the graph
+graphora risk top                   Riskiest symbols, ranked
+graphora benchmark PATH             Reproducible token-cost benchmark
+graphora serve-mcp                  Serve the graph to AI agents over MCP
+graphora install-skill [all|AGENT]  Install the Graphora skill for 22 AI coding agents
+graphora stats                      Node and edge counts
+```
+
+Every graph command accepts `--backend auto|falkordb|embedded` (default: auto).
+
+### 2. Python library
+
+```python
+from graphora import GraphStore, index_repository, blast_radius
+from graphora.blast import blast_radius_for_diff
+from graphora.risk import mine_risk_memory, risk_report
+
+store = index_repository("/path/to/repo")          # deterministic build
+mine_risk_memory(store, "/path/to/repo")           # teach it the history
+
+# CI gate: block changes to called-but-untested symbols, three lines
+radius = blast_radius_for_diff(store, pr_diff)
+untested = [s.name for s in radius.symbols if s.callers and not s.tests]
+assert not untested, f"Changed symbols with callers but no tests: {untested}"
+```
+
+### 3. MCP server (for AI agents)
+
+```bash
+graphora serve-mcp --project myrepo
+```
+
+Exposes `blast_radius`, `review_diff`, `risk_top`, `find_symbol`, and `graph_stats` to Copilot CLI, Claude Code, Cursor, or any MCP client. The server instructs agents to check the blast radius *before* editing a symbol, which turns Graphora into a guardrail for AI-generated changes.
+
+### 4. One-command skill install (22 agents)
+
+```bash
+graphora install-skill all          # or: graphora install-skill claude-code cursor copilot
+graphora install-skill --list      # see all supported agents
+```
+
+Writes the Graphora workflow rule (check blast radius before editing, run a grounded review before committing, consult risk memory) into each agent's project config: `.claude/skills/`, `.cursor/rules/`, `.github/instructions/`, `AGENTS.md`, `GEMINI.md`, Windsurf, Cline, Roo, Continue, Amazon Q, Zed, Goose, Aider, and more. Idempotent; existing files are preserved, shared files get a marked block.
+
+## Risk memory: the graph learns where the codebase breaks
+
+Graphora mines git history (deterministically, zero LLM) for fix, hotfix, bugfix, and revert commits, and attributes each one to the exact functions and classes it touched, using both diff lines and hunk-header context.
+
+```
+risk_score = (1 - 0.7^fix_count) * 0.5^(months_since_last_fix / 6)
+```
+
+A symbol fixed often and recently scores near 1.0. A quiet area decays by half every 6 months. Reviews then carry findings no stateless tool can produce:
+
+> **risk-memory** `falkordb/asyncio/cluster.py:9`: `Is_Cluster` was involved in 2 past fix/revert commits (last: 2025-03-13), risk score 0.08, 2 callers. Review extra carefully.
+
+The longer Graphora runs on a repository, the smarter it gets. That compounds.
+
+## Benchmarks
+
+Measured on real repositories, fully deterministic, zero network. Full methodology and reproduction commands in [BENCHMARKS.md](./BENCHMARKS.md).
+
+Public benchmark on pinned OSS commits, reproducible with `python3 scripts/public_benchmark.py`:
+
+| Repository | Commit | Whole-repo dump | Relevant files | **Graphora blast radius** | Savings |
+| --- | --- | ---: | ---: | ---: | ---: |
+| flask | `36e4a824f3` | 147,390 tokens | 124,205 tokens | **21,534 tokens** | **85.4%** |
+| requests | `f361ead047` | 101,739 tokens | 80,360 tokens | **10,331 tokens** | **89.8%** |
+| click | `b67832c216` | 225,373 tokens | 190,236 tokens | **39,534 tokens** | **82.5%** |
+| falkordb-py | `971f1d124e` | 59,866 tokens | 40,638 tokens | **3,550 tokens** | **94.1%** |
+
+Graph build cost in LLM credits: **$0**, by construction. The "relevant files" column is the honest baseline: every file a reviewer would have to read to learn what the blast radius states directly.
+
+## Use cases
+
+Five real, captured scenarios in [USECASES.md](./USECASES.md):
+
+1. **Cross-file impact review with zero LLM**: a one-line diff, callers and covering tests read straight from the graph, ~197 tokens of context.
+2. **Risk hotspot mining on a real codebase**: 231 commits of falkordb-py history, the async cluster code correctly surfaced as the trouble spot.
+3. **AI agents over MCP**: a live stdio session calling `blast_radius`, `risk_top`, `find_symbol`.
+4. **A CI gate in three lines** of library code, plus incremental re-indexing.
+5. **Ambiguity honesty**: duplicate symbol names tagged `AMBIGUOUS` instead of silently guessed.
+
+## Architecture
+
+```text
+                        ┌────────────────────────────────────────────┐
+   source files ───────▶│  tree-sitter parse (deterministic, $0)     │
+   git history  ───────▶│  risk miner (fix/revert attribution, $0)   │
+                        └───────────────────┬────────────────────────┘
+                                            ▼
+                       code graph (FalkorDB or embedded)
+                 File · Function · Class · Module · FixCommit
+              CALLS / DEFINED_IN / IMPORTS / FIXED  (confidence-tagged)
+                                            │
+              ┌──────────────┬──────────────┼───────────────┬─────────────┐
+              ▼              ▼              ▼               ▼             ▼
+           CLI           library API     MCP server     benchmark    skill installer
+        (terminal)      (CI gates,      (AI agents)    (reproducible)  (22 agents)
+                         refactors)
+```
+
+Graph model per project: `graphora:{project}` in FalkorDB, or `~/.graphora/{project}.json` embedded. Incremental updates re-parse only changed files. The optional LLM review pass (litellm, any provider) receives the diff plus the compact blast radius, never the repository.
+
+## Enterprise notes
+
+- **Privacy**: the index path is fully local. No code, no metadata leaves the machine unless the optional `--llm` review is enabled, and then only the diff plus a few hundred tokens of graph facts are sent to *your* configured provider.
+- **Determinism**: identical input produces identical graphs, reviews, and benchmark numbers. No embeddings drift, no model version drift in the core.
+- **Multi-project**: one FalkorDB instance serves many project graphs (`graphora:{project}`), so a single shared server can back a whole team. Solo developers need no server at all (embedded backend).
+- **Auditability**: every review claim traces to a tagged graph fact; every risk score traces to specific commits (`FixCommit` nodes with sha, date, subject).
+- **Incremental cost**: re-index only changed files on push; risk mining is idempotent per commit.
+
+## Testing
+
+80 tests, all passing: parser (11 languages), FalkorDB store, embedded store (including backend-parity tests), blast radius, risk memory, CLI, MCP server, skill installer, and benchmarks. Integration tests run against a live FalkorDB and real scripted git repositories, and skip cleanly when FalkorDB is absent.
+
+```bash
+python3 -m pytest tests -q        # 80 passed
+```
+
+The test-per-phase methodology and the bugs the suite caught are documented in [USECASES.md](./USECASES.md#how-it-was-tested).
+
+## Requirements
+
+| Requirement | Version | Notes |
+| --- | --- | --- |
+| Python | 3.10+ | |
+| FalkorDB | optional | for the client-server backend; embedded backend needs nothing |
+| git | any | for risk memory mining |
+| litellm | optional | only for `review --llm` |
+| mcp | optional | only for `serve-mcp` |
+
+Languages indexed today: Python, JavaScript, TypeScript, Go, Java, Rust, C, C++, Ruby, PHP (tree-sitter grammars, regex fallback).
+
+## License
+
+MIT