--- title: "Awesome-Code-LLM vs CodeT5" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/huybery-awesome-code-llm-vs-salesforce-codet5" tools: ["huybery-awesome-code-llm", "salesforce-codet5"] --- # Awesome-Code-LLM vs CodeT5 *GraphCanon updated Oct 11, 2026* ## Verdict Pick Awesome-Code-LLM if awesome-Code-LLM is a curated repository focused on code-focused large language models (code-LLMs), providing insights into top-performing models, evaluation toolkits, and research papers; pick CodeT5 if codeT5 is a large language model for code understanding and generation, developed by Salesforce, and is released under the BSD-3-Clause license. [Awesome-Code-LLM](https://github.com/huybery/Awesome-Code-LLM) reports 1.3k GitHub stars, 75 forks, and 5 open issues, last pushed Dec 10, 2024. [CodeT5](https://arxiv.org/abs/2305.07922) has 3.1k stars, 486 forks, and 88 open issues, last pushed Jun 25, 2026. Figures are from public GitHub metadata via [Awesome-Code-LLM's repository](https://github.com/huybery/Awesome-Code-LLM) and [CodeT5's repository](https://github.com/salesforce/CodeT5). | | [Awesome-Code-LLM](/tools/huybery-awesome-code-llm.md) | [CodeT5](/tools/salesforce-codet5.md) | | --- | --- | --- | | Tagline | 👨💻 An awesome and curated list of best code-LLM for research. | Open Code LLMs for Code Understanding and Generation | | Stars | 1,295 | 3,093 | | Forks | 75 | 486 | | Open issues | 5 | 88 | | Language | - | Python | | Adopt for | Awesome-Code-LLM is a curated repository focused on code-focused large language models (code-LLMs), providing insights into top-performing models, evaluation toolkits, and research papers. | CodeT5 is a large language model for code understanding and generation, developed by Salesforce, and is released under the BSD-3-Clause license. | | Persona | - | - | | Runtime | - | - | | License | MIT License: Permissive open-source license that allows usage in virtually any project with little restrictions. | CodeT5 is released under the BSD-3-Clause license, which allows for free use, modification, and distribution, provided that the original copyright notice and disclaimer are included. | | Categories | Evaluation & Observability, LLM Frameworks | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Awesome-Code-LLM](/tools/huybery-awesome-code-llm.md) | [CodeT5](/tools/salesforce-codet5.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Archived (8%) | | Days since push | 669d | 84d | | Archived on GitHub | No | Yes | | Open issues (now) | 5 | 88 | | Stars delta | +5 (30d) | -5 (30d) | | Owner type | User | Organization | | Full report | [trust report](/tools/huybery-awesome-code-llm/trust.md) | [trust report](/tools/salesforce-codet5/trust.md) | ## Decision facts: Awesome-Code-LLM - **Requirements:** No specific requirements to use the repository for reference or evaluation, but contributions may involve technical knowledge and familiarity with code-LLMs. - **Adopt for:** Awesome-Code-LLM is a curated repository focused on code-focused large language models (code-LLMs), providing insights into top-performing models, evaluation toolkits, and research papers. - **License detail:** MIT License: Permissive open-source license that allows usage in virtually any project with little restrictions. ## Decision facts: CodeT5 - **Requirements:** Min 8 GB RAM; The model may require significant computational resources for training and inference. - **Adopt for:** CodeT5 is a large language model for code understanding and generation, developed by Salesforce, and is released under the BSD-3-Clause license. - **License detail:** CodeT5 is released under the BSD-3-Clause license, which allows for free use, modification, and distribution, provided that the original copyright notice and disclaimer are included. ## Choose when ### Choose Awesome-Code-LLM if… - License: Awesome-Code-LLM is MIT, CodeT5 is BSD-3-Clause. - Requirements: No specific requirements to use the repository for reference or evaluation, but contributions may involve technical knowledge and familiarity with code-LLMs.. - Tags unique to Awesome-Code-LLM: awesome. - Also covers Evaluation & Observability. - When you need a comprehensive list of state-of-the-art code generation LLMs with performance metrics such as HumanEval. ### Choose CodeT5 if… - License: CodeT5 is BSD-3-Clause, Awesome-Code-LLM is MIT. - Requirements: Min 8 GB RAM; The model may require significant computational resources for training and inference.. - Tags unique to CodeT5: code-intelligence, code-understanding, language-model. - Also covers Model Training. - When you need a tool specifically for code understanding and generation tasks, as CodeT5 is designed with a focus on these areas. ## When NOT to use Awesome-Code-LLM - When looking for a tool that provides pre-trained models with built-in APIs or services, as Awesome-Code-LLM is primarily a directory/collection of information without direct service provision. - If you require real-time interactive use-cases and need immediate API access to LLMs; this repository does not offer such functionality. - In scenarios where you need a single end-to-end solution for training your own code generation models, as the platform is focused on aggregating third-party resources and research rather than offering ## When NOT to use CodeT5 - If your project involves promoting or profiting from violence, hate, division, environmental destruction, abuse of human rights, or the destruction of people's physical and mental health, as these are ## Common questions ### What is the difference between Awesome-Code-LLM and CodeT5? Awesome-Code-LLM: 👨💻 An awesome and curated list of best code-LLM for research.. CodeT5: Open Code LLMs for Code Understanding and Generation. See the comparison table for live GitHub stats and shared categories. ### When should I choose Awesome-Code-LLM over CodeT5? Choose Awesome-Code-LLM over CodeT5 when License: Awesome-Code-LLM is MIT, CodeT5 is BSD-3-Clause; Requirements: No specific requirements to use the repository for reference or evaluation, but contributions may involve technical knowledge and familiarity with code-LLMs.; Tags unique to Awesome-Code-LLM: awesome; Also covers Evaluation & Observability; When you need a comprehensive list of state-of-the-art code generation LLMs with performance metrics such as HumanEval. ### When should I choose CodeT5 over Awesome-Code-LLM? Choose CodeT5 over Awesome-Code-LLM when License: CodeT5 is BSD-3-Clause, Awesome-Code-LLM is MIT; Requirements: Min 8 GB RAM; The model may require significant computational resources for training and inference.; Tags unique to CodeT5: code-intelligence, code-understanding, language-model; Also covers Model Training; When you need a tool specifically for code understanding and generation tasks, as CodeT5 is designed with a focus on these areas. ### When should I avoid Awesome-Code-LLM? When looking for a tool that provides pre-trained models with built-in APIs or services, as Awesome-Code-LLM is primarily a directory/collection of information without direct service provision. If you require real-time interactive use-cases and need immediate API access to LLMs; this repository does not offer such functionality. In scenarios where you need a single end-to-end solution for training your own code generation models, as the platform is focused on aggregating third-party resources and research rather than offering ### When should I avoid CodeT5? If your project involves promoting or profiting from violence, hate, division, environmental destruction, abuse of human rights, or the destruction of people's physical and mental health, as these are ### Is Awesome-Code-LLM or CodeT5 more popular on GitHub? CodeT5 has more GitHub stars (3,093 vs 1,295). Stars measure visibility, not whether either tool fits your constraints. ### Are Awesome-Code-LLM and CodeT5 open source? Yes - both are open-source projects on GitHub (Awesome-Code-LLM: MIT, CodeT5: BSD-3-Clause). ### Where can I find alternatives to Awesome-Code-LLM or CodeT5? GraphCanon lists graph-backed alternatives at [Awesome-Code-LLM alternatives](/tools/huybery-awesome-code-llm/alternatives) and [CodeT5 alternatives](/tools/salesforce-codet5/alternatives) ([Awesome-Code-LLM markdown twin](/tools/huybery-awesome-code-llm/alternatives.md), [CodeT5 markdown twin](/tools/salesforce-codet5/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/huybery-awesome-code-llm-vs-salesforce-codet5.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Awesome-Code-LLM or CodeT5? Awesome-Code-LLM: Dormant. CodeT5: 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 Awesome-Code-LLM and CodeT5? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Awesome-Code-LLM trust report](/tools/huybery-awesome-code-llm/trust); [CodeT5 trust report](/tools/salesforce-codet5/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=huybery-awesome-code-llm`](/api/graphcanon/graph?tool=huybery-awesome-code-llm) - 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/_