--- title: "repobench vs code-review-graph" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/leolty-repobench-vs-tirth8205-code-review-graph" tools: ["leolty-repobench", "tirth8205-code-review-graph"] --- # repobench vs code-review-graph *GraphCanon updated Jul 11, 2026* ## Verdict Pick repobench when license: repobench is CC-BY-4.0, code-review-graph is MIT; pick code-review-graph when license: code-review-graph is MIT, repobench is CC-BY-4.0. [repobench](https://arxiv.org/abs/2306.03091) reports 212 GitHub stars, 13 forks, and 12 open issues, last pushed Aug 16, 2024. [code-review-graph](https://code-review-graph.com) has 19k stars, 2.1k forks, and 185 open issues, last pushed Jun 14, 2026. Figures are from public GitHub metadata via [repobench's repository](https://github.com/Leolty/repobench) and [code-review-graph's repository](https://github.com/tirth8205/code-review-graph). | | [repobench](/tools/leolty-repobench.md) | [code-review-graph](/tools/tirth8205-code-review-graph.md) | | --- | --- | --- | | Tagline | ✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024 | 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 w | | Stars | 212 | 19,416 | | Forks | 13 | 2,078 | | Open issues | 12 | 185 | | Language | Python | Python | | Adopt for | - | - | | Persona | - | - | | Runtime | - | - | | License | CC-BY-4.0 | MIT | | Categories | Evaluation & Observability | Developer Tools, Evaluation & Observability, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [repobench](/tools/leolty-repobench.md) | [code-review-graph](/tools/tirth8205-code-review-graph.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Active (82%) | | Days since push | 694d | 26d | | Open issues (now) | 12 | 185 | | Security scan | No criticals | No MCP manifest | | Full report | [trust report](/tools/leolty-repobench/trust.md) | [trust report](/tools/tirth8205-code-review-graph/trust.md) | ## Choose when ### Choose repobench if… - License: repobench is CC-BY-4.0, code-review-graph is MIT. - Tags unique to repobench: python. - Leaner open-issue backlog (12). ### Choose code-review-graph if… - License: code-review-graph is MIT, repobench is CC-BY-4.0. - Tags unique to code-review-graph: ai-coding, claude, claude-code, code-review. - Also covers Developer Tools, LLM Frameworks. ## When NOT to use repobench - Last GitHub push was 695 days ago (dormant maintenance, Aug 16, 2024). Validate activity before betting a new project on repobench. - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. ## When NOT to use code-review-graph - Developer Tools: A gateway is overkill when you're pinned to a single provider and model. - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ## Common questions ### What is the difference between repobench and code-review-graph? repobench: ✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024. code-review-graph: 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 w. See the comparison table for live GitHub stats and shared categories. ### When should I choose repobench over code-review-graph? Choose repobench over code-review-graph when License: repobench is CC-BY-4.0, code-review-graph is MIT; Tags unique to repobench: python; Leaner open-issue backlog (12). ### When should I choose code-review-graph over repobench? Choose code-review-graph over repobench when License: code-review-graph is MIT, repobench is CC-BY-4.0; Tags unique to code-review-graph: ai-coding, claude, claude-code, code-review; Also covers Developer Tools, LLM Frameworks. ### When should I avoid repobench? Last GitHub push was 695 days ago (dormant maintenance, Aug 16, 2024). Validate activity before betting a new project on repobench. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. ### When should I avoid code-review-graph? Developer Tools: A gateway is overkill when you're pinned to a single provider and model. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ### Is repobench or code-review-graph more popular on GitHub? code-review-graph has more GitHub stars (19,416 vs 212). Stars measure visibility, not whether either tool fits your constraints. ### Are repobench and code-review-graph open source? Yes - both are open-source projects on GitHub (repobench: CC-BY-4.0, code-review-graph: MIT). ### Where can I find alternatives to repobench or code-review-graph? GraphCanon lists graph-backed alternatives at [repobench alternatives](/tools/leolty-repobench/alternatives) and [code-review-graph alternatives](/tools/tirth8205-code-review-graph/alternatives) ([repobench markdown twin](/tools/leolty-repobench/alternatives.md), [code-review-graph markdown twin](/tools/tirth8205-code-review-graph/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/leolty-repobench-vs-tirth8205-code-review-graph.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, repobench or code-review-graph? repobench: Dormant. code-review-graph: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for repobench and code-review-graph? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [repobench trust report](/tools/leolty-repobench/trust); [code-review-graph trust report](/tools/tirth8205-code-review-graph/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=leolty-repobench`](/api/graphcanon/graph?tool=leolty-repobench) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_