{"data":{"slug":"tirth8205-code-review-graph","name":"code-review-graph","tagline":"Local-first code intelligence graph for AI coding tools","github_url":"https://github.com/tirth8205/code-review-graph","owner":"tirth8205","repo":"code-review-graph","owner_avatar_url":"https://avatars.githubusercontent.com/u/68604113?v=4","primary_language":"Python","stars":31569,"forks":2871,"topics":["ai-coding","claude","claude-code","code-review","graphrag","incremental","knowledge-graph","llm","mcp","python","static-analysis","tree-sitter"],"archived":false,"github_pushed_at":"2026-09-17T01:47:04+00:00","maintenance_label":"Very active","stars_delta_30d":5127,"url":"https://www.graphcanon.com/tools/tirth8205-code-review-graph","markdown_url":"https://www.graphcanon.com/tools/tirth8205-code-review-graph.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tirth8205-code-review-graph","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tirth8205-code-review-graph","description":"Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.","homepage_url":"https://code-review-graph.com","license":"MIT","open_issues":135,"watchers":102,"ai_summary":"Builds a persistent map of your codebase to optimize AI coding tool interactions, reducing context and improving performance in code reviews and large-repo workflows.","readme_excerpt":"## Quick Start\n\n```bash\npip install code-review-graph          # or: pipx install code-review-graph\ncode-review-graph install              # detect installed AI coding tools and configure each one\ncode-review-graph build                # parse the codebase\n```\n\n`install` detects which AI coding tools you have, writes an MCP server entry for each, installs hooks and skills where the platform supports them, and adds graph instructions to the platform's rules file. The MCP entry uses `poetry run` or `uv run` inside a Poetry or uv project environment, `uvx code-review-graph serve` when `uvx` is on PATH, and otherwise the current Python interpreter. Restart the editor or tool afterwards.\n\n<p align=\"center\">\n  <img src=\"diagrams/diagram8_supported_platforms.png\" alt=\"One install, every platform: detects Codex, Claude Code, CodeBuddy Code, Cursor, Windsurf, Zed, Continue, OpenCode, Antigravity, Gemini CLI, Qwen, Qoder, Kiro, GitHub Copilot, GitHub Copilot CLI, and Hermes Agent\" width=\"85%\" />\n</p>\n\nTo configure one platform, pass `--platform` with one of `codex`, `claude-code`, `cursor`, `windsurf`, `zed`, `continue`, `opencode`, `antigravity`, `gemini-cli`, `qwen`, `kiro`, `qoder`, `copilot`, `copilot-cli`, `codebuddy`, or `hermes`:\n\n```bash\ncode-review-graph install --platform cursor\ncode-review-graph install --platform codebuddy\n```\n\nConfig file locations are listed in [docs/USAGE.md](docs/USAGE.md#supported-platforms). Requires Python 3.10+.\n\n`uninstall` removes CRG-owned files and entries from a Git or SVN working tree and leaves other MCP servers, hooks, skills and JSONC comments alone. Run it from anywhere inside the tree. Shared config files are replaced atomically, so a failed write leaves the original intact.\n\n```bash\ncode-review-graph uninstall --dry-run    # preview only\ncode-review-graph uninstall              # preview, confirm, apply\ncode-review-graph uninstall --yes        # apply without prompting\ncode-review-graph uninstall --all-repos  # also clean every registered repository\ncode-review-graph uninstall --keep-data  # remove integrations, keep graph databases\ncode-review-graph uninstall --keep-user-configs --repo .  # this project only\n```\n\nThen open the project and ask the assistant:\n\n```\nBuild the code review graph for this project\n```\n\nBuild time scales with repository size; a cold build of a ~3,000-file repository took about 40 seconds ([measured](docs/REPRODUCING.md#incremental-update-latency)). After that, hooks and watch mode keep the graph updated. If some files fail to parse, the result has status `partial` and names them in its summary; the CLI also prints a `Warning:` line on stderr, and those files keep their previous graph rows.","github_created_at":"2026-02-26T17:25:13+00:00","created_at":"2026-07-11T11:48:22.08343+00:00","updated_at":"2026-09-20T04:32:54.963211+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai-coding","name":"ai-coding"},{"slug":"claude","name":"claude"},{"slug":"code-review","name":"code-review"},{"slug":"graph","name":"graph"},{"slug":"incremental","name":"incremental"},{"slug":"knowledge-graph","name":"knowledge-graph"},{"slug":"llm","name":"llm"},{"slug":"mcp","name":"mcp"}],"trust":{"provenance":{"is_fork":false,"github_id":1167788341,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:43:31.439Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":1,"last_release_at":"2026-08-21T22:37:47Z","stars_delta_30d":5127,"open_issues_delta_30d":13},"security_summary":{"status":"findings","scanner":"mcp_manifest@v1","low_count":2,"high_count":0,"last_scan_at":"2026-09-18T08:43:33.808Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:43:30.294Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-18T08:43:30.294Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:43:30.294Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:43:30.294Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Python 3.10+."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["When you need to optimize AI coding tool interactions in large codebases, as it builds a persistent map of your codebase to reduce context and improve performance.","If you are working with multiple AI coding tools, as it detects installed tools and configures each one to work with the graph.","For projects that require incremental updates and static analysis, as it supports incremental builds and uses tree-sitter for parsing."],"when_not_to_use":["If your project does not require integration with multiple AI coding tools, as the tool is designed to work with a variety of platforms and may introduce unnecessary complexity.","When you are working with small codebases where the overhead of building and maintaining a code intelligence graph outweighs the benefits.","If you are using a language other than Python, as the tool is specifically designed for Python projects and may not support other languages as effectively."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:14:43.405Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Requires Python 3.10+."},{"label":"Adopt for","value":"code-review-graph is a Python-based tool that creates a local-first code intelligence graph to optimize AI coding tool interactions, reducing context and improving performance in code reviews and large-repo workflows."},{"label":"License detail","value":"MIT License"}]}}