--- title: "CodeT5 vs self-repair" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/salesforce-codet5-vs-theoxo-self-repair" tools: ["salesforce-codet5", "theoxo-self-repair"] --- # CodeT5 vs self-repair *GraphCanon updated Aug 5, 2026* ## Verdict Pick CodeT5 if codeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license; pick self-repair if self-repair provides tools to replicate research experiments on code generation systems self-reparation techniques. [CodeT5](https://arxiv.org/abs/2305.07922) reports 3.1k GitHub stars, 487 forks, and 88 open issues, last pushed Jun 25, 2026. [self-repair](https://github.com/theoxo/self-repair) has 15 stars, 3 forks, and 1 open issues, last pushed May 2, 2024. Figures are from public GitHub metadata via [CodeT5's repository](https://github.com/salesforce/CodeT5) and [self-repair's repository](https://github.com/theoxo/self-repair). | | [CodeT5](/tools/salesforce-codet5.md) | [self-repair](/tools/theoxo-self-repair.md) | | --- | --- | --- | | Tagline | Home of CodeT5: Open Code LLMs for Code Understanding and Generation | Supports research on self-repair mechanisms for code generation | | Stars | 3,098 | 15 | | Forks | 487 | 3 | | Open issues | 88 | 1 | | Language | Python | Python | | Adopt for | CodeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license. | Self-repair provides tools to replicate research experiments on code generation systems self-reparation techniques. | | Persona | - | - | | Runtime | - | - | | License | BSD-3-Clause | - | | Categories | Developer Tools, LLM Frameworks | Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [CodeT5](/tools/salesforce-codet5.md) | [self-repair](/tools/theoxo-self-repair.md) | | --- | --- | --- | | Days since push | 38d | 825d | | Open issues (now) | 88 | 1 | | Owner type | Organization | User | | Full report | [trust report](/tools/salesforce-codet5/trust.md) | [trust report](/tools/theoxo-self-repair/trust.md) | ## Decision facts: CodeT5 - **Adopt for:** CodeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license. ## Decision facts: self-repair - **Adopt for:** Self-repair provides tools to replicate research experiments on code generation systems self-reparation techniques. ## Choose when ### Choose CodeT5 if… - Tags unique to CodeT5: code generation, code-intelligence, code-understanding, language-model. - Also covers LLM Frameworks. - When focusing on Python projects needing advanced code understanding or generation. ### Choose self-repair if… - Tags unique to self-repair: code-repair, experiments replication, python, research-tools. - When aiming to replicate specific experimental data from the ICLR 2024 paper on self-repair in code generation - Leaner open-issue backlog (1). ## When NOT to use CodeT5 - If the project requires proprietary licensing protection, given its open-source nature under BSD-3-Clause. - Avoid if real-time performance is a crucial requirement since LLMs typically lag in speed. ## When NOT to use self-repair - For creating entirely new datasets or conducting large-scale human studies, as this repository focuses on replicating existing experiments - When the internal dependencies or incomplete code functions such as exec_sample in APPS are critical for your application without modification ## Common questions ### What is the difference between CodeT5 and self-repair? CodeT5: Home of CodeT5: Open Code LLMs for Code Understanding and Generation. self-repair: Supports research on self-repair mechanisms for code generation. See the comparison table for live GitHub stats and shared categories. ### When should I choose CodeT5 over self-repair? Choose CodeT5 over self-repair when Tags unique to CodeT5: code generation, code-intelligence, code-understanding, language-model; Also covers LLM Frameworks; When focusing on Python projects needing advanced code understanding or generation. ### When should I choose self-repair over CodeT5? Choose self-repair over CodeT5 when Tags unique to self-repair: code-repair, experiments replication, python, research-tools; When aiming to replicate specific experimental data from the ICLR 2024 paper on self-repair in code generation; Leaner open-issue backlog (1). ### When should I avoid CodeT5? If the project requires proprietary licensing protection, given its open-source nature under BSD-3-Clause. Avoid if real-time performance is a crucial requirement since LLMs typically lag in speed. ### When should I avoid self-repair? For creating entirely new datasets or conducting large-scale human studies, as this repository focuses on replicating existing experiments When the internal dependencies or incomplete code functions such as exec_sample in APPS are critical for your application without modification ### Is CodeT5 or self-repair more popular on GitHub? CodeT5 has more GitHub stars (3,098 vs 15). Stars measure visibility, not whether either tool fits your constraints. ### Are CodeT5 and self-repair open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to CodeT5 or self-repair? GraphCanon lists graph-backed alternatives at [CodeT5 alternatives](/tools/salesforce-codet5/alternatives) and [self-repair alternatives](/tools/theoxo-self-repair/alternatives) ([CodeT5 markdown twin](/tools/salesforce-codet5/alternatives.md), [self-repair markdown twin](/tools/theoxo-self-repair/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/salesforce-codet5-vs-theoxo-self-repair.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, CodeT5 or self-repair? CodeT5: Archived. self-repair: Archived. 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 CodeT5 and self-repair? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [CodeT5 trust report](/tools/salesforce-codet5/trust); [self-repair trust report](/tools/theoxo-self-repair/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=salesforce-codet5`](/api/graphcanon/graph?tool=salesforce-codet5) - 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/_