{"data":{"slug":"salesforce-coderl","name":"CodeRL","tagline":"CodeRL: Combines pretrained models and reinforcement learning for code generation.","github_url":"https://github.com/salesforce/CodeRL","owner":"salesforce","repo":"CodeRL","owner_avatar_url":"https://avatars.githubusercontent.com/u/453694?v=4","primary_language":"Python","stars":574,"forks":69,"topics":["ai","codegeneration","languagemodel","machinelearning","programsynthesis","reinforcementlearning"],"archived":false,"github_pushed_at":"2026-06-02T18:14:33+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/salesforce-coderl","markdown_url":"https://www.graphcanon.com/tools/salesforce-coderl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/salesforce-coderl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=salesforce-coderl","description":"This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).","homepage_url":null,"license":"BSD-3-Clause","open_issues":42,"watchers":15,"ai_summary":"Official implementation of CodeRL, which uses deep reinforcement learning with pretrained language models to master code generation tasks. Built on top of Hugging Face's transformers library version 4.16.1.","readme_excerpt":"## Installation  \n\nThe code requires some dependencies as specified in `requirements.txt`. Please follow the relevant libraries to install or run: \n\n`pip install -r requirements.txt`\n\nInstall the `transformers` library from the source code (the current source code is developed from the original [code](https://github.com/huggingface/transformers) of version 4.16.1): \n\n```\ncd transformers\npip install -e .\n```\n\n---\n\n## License \n\nThe code is released under BSD 3-Clause - see `LICENSE.txt` for details.\n\nThis code is developed from other open source projects: including [APPS](https://github.com/hendrycks/apps/), [HumanEval](https://github.com/openai/human-eval), and [transformers](https://github.com/huggingface/transformers). We thank the original contributors of these works for open-sourcing their valuable source codes.","github_created_at":"2022-06-30T02:54:36+00:00","created_at":"2026-07-11T23:44:43.759198+00:00","updated_at":"2026-08-05T12:02:17.172891+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"codegeneration","name":"codegeneration"},{"slug":"languagemodel","name":"languagemodel"},{"slug":"machinelearning","name":"machinelearning"},{"slug":"programsynthesis","name":"programsynthesis"},{"slug":"reinforcementlearning","name":"reinforcementlearning"}],"trust":{"provenance":{"is_fork":false,"github_id":508912853,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-05T12:02:16.356Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":63,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":29,"high_count":0,"last_scan_at":"2026-07-11T23:44:45.778Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-05T12:02:16.864Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-05T12:02:16.864Z"},"license_spdx":{"value":"BSD-3-Clause","source":"github.license","observed_at":"2026-08-05T12:02:16.864Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to generate complex and context-aware code snippets utilizing the latest in reinforcement learning techniques.","For projects where integration with Hugging Face's transformers library version 4.16.1 is desirable."],"when_not_to_use":["Avoid if your project requires only simple, quick code generation without deep reinforcement learning support.","Do not use if compatibility with versions of the Hugging Face transformers library other than 4.16.1 is critical to avoid potential issues."],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:10:07.890Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"CodeRL is an advanced tool that uses pretrained models and deep reinforcement learning to generate code."}]}}