tech-srl/code2vec

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1147 stars · 290 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official TensorFlow implementation of the code2vec model from the POPL'2019 paper, which learns distributed vector representations of code snippets from abstract syntax tree paths. It is trained by default to predict Java method names but is language-agnostic and intended for research in machine learning on code.

Use cases

• generate vector embeddings for code snippets
• predict method names from Java code
• research machine learning on source code
• train a code representation model on a new programming language
• extract code2vec embeddings for downstream ML tasks
• reproduce results from the code2vec paper

When to choose

• you need code embeddings based on AST paths for research or classification
• you want to experiment with neural models of source code in TensorFlow
• you want to reproduce or extend the code2vec model

When to avoid

• you need a production-ready code intelligence service
• you want modern transformer-based code models like CodeBERT
• you need active development or new features
• you don't work in Python/TensorFlow

Facets

library · maturity maintenance

machine-learning deep-learning nlp parser machine-learning programming-languages developer-tools artificial-intelligence python cross-platform code-embeddings tensorflow research code-analysis method-name-prediction academic

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tech-srl/code2vec")