Comparison
LLM4Decompile vs CodeT5
Verdict
Pick LLM4Decompile if lLM4Decompile uses large language models to reverse engineer binary code into assembly instructions and potentially source code; pick CodeT5 if codeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license.
Markdown twin · LLM4Decompile alternatives · CodeT5 alternatives
GraphCanon updated 3d
vs
Trust & integrity
| Signal | LLM4Decompile | CodeT5 |
|---|---|---|
| Maintenance | Slowing (186d since push) As of 3d · github_public_v1 | Archived (38d since push) As of 2w · github_public_v1 |
| Provenance | Not a fork · Personal account As of 3d · github_public_v1 | Not a fork · Organization account As of 2w · github_public_v1 |
| OSV dependency advisories | Published findings As of 1mo · osv@v1 | No lockfile (source not queried) As of 1mo · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- LLM4Decompile
- Decompiling Binary Code with Large Language Models
- CodeT5
- Home of CodeT5: Open Code LLMs for Code Understanding and Generation
Stars
- LLM4Decompile
- 7.0k
- CodeT5
- 3.1k
Forks
- LLM4Decompile
- 546
- CodeT5
- 487
Open issues
- LLM4Decompile
- 46
- CodeT5
- 88
Language
- LLM4Decompile
- Python
- CodeT5
- Python
Adopt for
- LLM4Decompile
- LLM4Decompile uses large language models to reverse engineer binary code into assembly instructions and potentially source code.
- CodeT5
- CodeT5, an open-source LLM for code understanding and generation under BSD-3-Clause license.
Persona
- LLM4Decompile
- -
- CodeT5
- -
Runtime
- LLM4Decompile
- -
- CodeT5
- -
License
- LLM4Decompile
- MIT
- CodeT5
- BSD-3-Clause
Last pushed
- LLM4Decompile
- Feb 12, 2026
- CodeT5
- Jun 25, 2026
Categories
- LLM4Decompile
- LLM Frameworks
- CodeT5
- Developer Tools, LLM Frameworks
Trust and health
Maintenance
- LLM4Decompile
- Slowing (36%)
- CodeT5
- Archived (8%)
Days since push
- LLM4Decompile
- 186d
- CodeT5
- 38d
Archived on GitHub
- LLM4Decompile
- No
- CodeT5
- Yes
Open issues (now)
- LLM4Decompile
- 46
- CodeT5
- 88
Stars delta
- LLM4Decompile
- +205 (30d)
- CodeT5
- Unknown
Open issues delta
- LLM4Decompile
- 0 (30d)
- CodeT5
- Unknown
Owner type
- LLM4Decompile
- User
- CodeT5
- Organization
OSV dependency advisories
- LLM4Decompile
- Published findings
- CodeT5
- No lockfile (source not queried)
Full report
- LLM4Decompile
- Trust report
- CodeT5
- Trust report
Choose LLM4Decompile if…
- License: LLM4Decompile is MIT, CodeT5 is BSD-3-Clause.
- Pricing: The tool itself is open-source under the MIT license, but using it effectively may require access to specific large language models that could have associated costs..
- Requirements: Min 16 GB RAM; Requires a GPU for optimal performance with the specified model..
- Tags unique to LLM4Decompile: binary, decompile, reverse-engineering.
- LLM4Decompile ships Docker support for self-hosted deployment.
- When you need a tool that leverages advanced language models for decompiling binaries more effectively than traditional methods.
When NOT to use LLM4Decompile
- Avoid this tool if you require high precision in recreating exact source code, especially for heavily optimized binaries that lose contextual information during compilation.
- Do not use LLM4Decompile when working with less common architectures (e.g., RISC-V) unless explicitly supported or tested by the model.
Choose CodeT5 if…
- License: CodeT5 is BSD-3-Clause, LLM4Decompile is MIT.
- Tags unique to CodeT5: code generation, code-intelligence, code-understanding, language-model.
- Also covers Developer Tools.
- When focusing on Python projects needing advanced code understanding or generation.
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.
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (albertan017/LLM4Decompile) · observed Aug 17, 2026
- GitHub forks (albertan017/LLM4Decompile) · observed Aug 17, 2026
- Last push (albertan017/LLM4Decompile) · observed Feb 12, 2026
- License file (MIT) · observed Aug 17, 2026
- Decision facts (enrichment) · observed Jul 12, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (salesforce/CodeT5) · observed Aug 2, 2026
- GitHub forks (salesforce/CodeT5) · observed Aug 2, 2026
- Last push (salesforce/CodeT5) · observed Jun 25, 2026
- License file (BSD-3-Clause) · observed Aug 2, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: LLM4Decompile 7.0k · CodeT5 3.1k (synced Aug 17, 2026).
Common questions
- What is the difference between LLM4Decompile and CodeT5?
- LLM4Decompile: Decompiling Binary Code with Large Language Models. CodeT5: Home of CodeT5: Open Code LLMs for Code Understanding and Generation. See the comparison table for live GitHub stats and shared categories.
- When should I choose LLM4Decompile over CodeT5?
- Choose LLM4Decompile over CodeT5 when License: LLM4Decompile is MIT, CodeT5 is BSD-3-Clause; Pricing: The tool itself is open-source under the MIT license, but using it effectively may require access to specific large language models that could have associated costs.; Requirements: Min 16 GB RAM; Requires a GPU for optimal performance with the specified model.; Tags unique to LLM4Decompile: binary, decompile, reverse-engineering; LLM4Decompile ships Docker support for self-hosted deployment; When you need a tool that leverages advanced language models for decompiling binaries more effectively than traditional methods.
- When should I choose CodeT5 over LLM4Decompile?
- Choose CodeT5 over LLM4Decompile when License: CodeT5 is BSD-3-Clause, LLM4Decompile is MIT; Tags unique to CodeT5: code generation, code-intelligence, code-understanding, language-model; Also covers Developer Tools; When focusing on Python projects needing advanced code understanding or generation.
- When should I avoid LLM4Decompile?
- Avoid this tool if you require high precision in recreating exact source code, especially for heavily optimized binaries that lose contextual information during compilation. Do not use LLM4Decompile when working with less common architectures (e.g., RISC-V) unless explicitly supported or tested by the model.
- 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.
- Is LLM4Decompile or CodeT5 more popular on GitHub?
- LLM4Decompile has more GitHub stars (6,965 vs 3,098). Stars measure visibility, not whether either tool fits your constraints.
- Are LLM4Decompile and CodeT5 open source?
- Yes - both are open-source projects on GitHub (LLM4Decompile: MIT, CodeT5: BSD-3-Clause).
- Where can I find alternatives to LLM4Decompile or CodeT5?
- GraphCanon lists graph-backed alternatives at LLM4Decompile alternatives and CodeT5 alternatives (LLM4Decompile markdown twin, CodeT5 markdown twin), 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 mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, LLM4Decompile or CodeT5?
- LLM4Decompile: Slowing. 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 LLM4Decompile and CodeT5?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: LLM4Decompile trust report; CodeT5 trust report.