---
title: "Awesome-Code-LLM vs MGDebugger"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/huybery-awesome-code-llm-vs-yerbapage-mgdebugger"
tools: ["huybery-awesome-code-llm", "yerbapage-mgdebugger"]
---

# Awesome-Code-LLM vs MGDebugger

*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 MGDebugger if mGDebugger offers hierarchical debugging for various levels of code granularity, emphasizing efficient error resolution and improved debug accuracy.

[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. [MGDebugger](https://github.com/YerbaPage/MGDebugger) has 101 stars, 10 forks, and 1 open issues, last pushed Jul 6, 2025. Figures are from public GitHub metadata via [Awesome-Code-LLM's repository](https://github.com/huybery/Awesome-Code-LLM) and [MGDebugger's repository](https://github.com/YerbaPage/MGDebugger).

| | [Awesome-Code-LLM](/tools/huybery-awesome-code-llm.md) | [MGDebugger](/tools/yerbapage-mgdebugger.md) |
| --- | --- | --- |
| Tagline | 👨💻 An awesome and curated list of best code-LLM for research. | Multi-Granularity LLM Debugger |
| Stars | 1,295 | 101 |
| Forks | 75 | 10 |
| Open issues | 5 | 1 |
| 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. | MGDebugger offers hierarchical debugging for various levels of code granularity, emphasizing efficient error resolution and improved debug accuracy. |
| Persona | - | - |
| Runtime | - | - |
| License | MIT License: Permissive open-source license that allows usage in virtually any project with little restrictions. | MIT |
| Categories | Evaluation & Observability, LLM Frameworks | Evaluation & Observability, LLM Frameworks |

## Trust and health

_Sourced signals - not a safety guarantee. No winner column._

| | [Awesome-Code-LLM](/tools/huybery-awesome-code-llm.md) | [MGDebugger](/tools/yerbapage-mgdebugger.md) |
| --- | --- | --- |
| Days since push | 669d | 458d |
| Open issues (now) | 5 | 1 |
| Stars delta | +5 (30d) | 0 (30d) |
| Open issues delta | 0 (30d) | +1 (30d) |
| Full report | [trust report](/tools/huybery-awesome-code-llm/trust.md) | [trust report](/tools/yerbapage-mgdebugger/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: MGDebugger

- **Pricing:** freemium - MGDebugger is free to use under MIT license but may require users to manage model hosting costs and dependencies.
- **Requirements:** Min 4 GB RAM; Requires Python version 3.8 or later; vLLM version 0.6.0 or later must be installed for model inference
- **Adopt for:** MGDebugger offers hierarchical debugging for various levels of code granularity, emphasizing efficient error resolution and improved debug accuracy.

## Choose when

### Choose Awesome-Code-LLM if…

- 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.
- When you need a comprehensive list of state-of-the-art code generation LLMs with performance metrics such as HumanEval.

### Choose MGDebugger if…

- Pricing: MGDebugger is free to use under MIT license but may require users to manage model hosting costs and dependencies..
- Requirements: Min 4 GB RAM; Requires Python version 3.8 or later; vLLM version 0.6.0 or later must be installed for model inference.
- Tags unique to MGDebugger: automatic-program-repair, debugger, llm, programming-languages.
- When you need to perform granular analysis on complex codes, progressing from subfunctions to the whole system to ensure precise error detection and correction.

## 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 MGDebugger

- Avoid using MGDebugger if you operate primarily on Mac systems and do not require support for quantized models (as some essential dependencies are unsupported on MacOS).
- If your model does not align well with the DeepSeek-Coder-V2-Lite-Instruct or similar models, since the effectiveness of MGDebugger might vary without support for those particular frameworks.

## Common questions

### What is the difference between Awesome-Code-LLM and MGDebugger?

Awesome-Code-LLM: 👨💻 An awesome and curated list of best code-LLM for research.. MGDebugger: Multi-Granularity LLM Debugger. See the comparison table for live GitHub stats and shared categories.

### When should I choose Awesome-Code-LLM over MGDebugger?

Choose Awesome-Code-LLM over MGDebugger when 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; When you need a comprehensive list of state-of-the-art code generation LLMs with performance metrics such as HumanEval.

### When should I choose MGDebugger over Awesome-Code-LLM?

Choose MGDebugger over Awesome-Code-LLM when Pricing: MGDebugger is free to use under MIT license but may require users to manage model hosting costs and dependencies.; Requirements: Min 4 GB RAM; Requires Python version 3.8 or later; vLLM version 0.6.0 or later must be installed for model inference; Tags unique to MGDebugger: automatic-program-repair, debugger, llm, programming-languages; When you need to perform granular analysis on complex codes, progressing from subfunctions to the whole system to ensure precise error detection and correction.

### 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 MGDebugger?

Avoid using MGDebugger if you operate primarily on Mac systems and do not require support for quantized models (as some essential dependencies are unsupported on MacOS). If your model does not align well with the DeepSeek-Coder-V2-Lite-Instruct or similar models, since the effectiveness of MGDebugger might vary without support for those particular frameworks.

### Is Awesome-Code-LLM or MGDebugger more popular on GitHub?

Awesome-Code-LLM has more GitHub stars (1,295 vs 101). Stars measure visibility, not whether either tool fits your constraints.

### Are Awesome-Code-LLM and MGDebugger open source?

Yes - both are open-source projects on GitHub (Awesome-Code-LLM: MIT, MGDebugger: MIT).

### Where can I find alternatives to Awesome-Code-LLM or MGDebugger?

GraphCanon lists graph-backed alternatives at [Awesome-Code-LLM alternatives](/tools/huybery-awesome-code-llm/alternatives) and [MGDebugger alternatives](/tools/yerbapage-mgdebugger/alternatives) ([Awesome-Code-LLM markdown twin](/tools/huybery-awesome-code-llm/alternatives.md), [MGDebugger markdown twin](/tools/yerbapage-mgdebugger/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-yerbapage-mgdebugger.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 MGDebugger?

Awesome-Code-LLM: Dormant. MGDebugger: Dormant. 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 MGDebugger?

GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Awesome-Code-LLM trust report](/tools/huybery-awesome-code-llm/trust); [MGDebugger trust report](/tools/yerbapage-mgdebugger/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/_