{"id":17103205,"url":"https://github.com/pravj/semantris-solver","last_synced_at":"2026-02-19T19:32:28.402Z","repository":{"id":37779265,"uuid":"150839498","full_name":"pravj/semantris-solver","owner":"pravj","description":"Automated solver for Semantris using OpenCV and Word Embeddings","archived":false,"fork":false,"pushed_at":"2022-12-08T02:54:57.000Z","size":288,"stargazers_count":13,"open_issues_count":13,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-10-20T04:56:40.145Z","etag":null,"topics":["google-experiment","hack","ocr","opencv","semantris","tesseract","word-embedding","word2vec"],"latest_commit_sha":null,"homepage":"https://hackpravj.com/blog/solving-semantris-opencv-word2vec/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pravj.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-09-29T07:51:44.000Z","updated_at":"2025-10-17T02:39:18.000Z","dependencies_parsed_at":"2023-01-24T21:15:43.718Z","dependency_job_id":null,"html_url":"https://github.com/pravj/semantris-solver","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pravj/semantris-solver","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pravj%2Fsemantris-solver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pravj%2Fsemantris-solver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pravj%2Fsemantris-solver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pravj%2Fsemantris-solver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pravj","download_url":"https://codeload.github.com/pravj/semantris-solver/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pravj%2Fsemantris-solver/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29628809,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-19T18:02:07.722Z","status":"ssl_error","status_checked_at":"2026-02-19T18:01:46.144Z","response_time":117,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["google-experiment","hack","ocr","opencv","semantris","tesseract","word-embedding","word2vec"],"created_at":"2024-10-14T15:32:20.404Z","updated_at":"2026-02-19T19:32:28.374Z","avatar_url":"https://github.com/pravj.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"semantris-solver\n================\n\u003e Automated solver for [Semantris](https://research.google.com/semantris/) using OpenCV and Word Embeddings\n\n---\n\n#### Setup\n###### Clone the repository\n```\ngit clone git@github.com:pravj/semantris-solver.git\n```\n\n###### Setup Python environment with the required packages\n```\npip install -r requirements.txt\n```\n\n###### Setup OpenCV and Tesseract\n- Install OpenCV and Tesseract for your OS\n\n###### Setup word embeddings\n- Download [pre-trained word2vec](https://github.com/mmihaltz/word2vec-GoogleNews-vectors) from Google News corpus\n- Set the model path as an environment variable *SEMANTRIS_SOLVER_WORD2VEC_PATH*\n```\nexport SEMANTRIS_SOLVER_WORD2VEC_PATH=/path/to/GoogleNews-vectors-negative300.bin\n```\n\n---\n\n#### Usage\n```\nSemantris Solver\n\nUsage:\n  main.py play [--mode=\u003cmode\u003e] [--verbose]\n  main.py (-h | --help)\n  main.py --version\n\nOptions:\n  -h --help      Show this screen\n  --version      Show version\n  --verbose      Print game activity logs\n  --mode=\u003cmode\u003e  Semantris game mode [default: arcade]\n```\n\n- For now it only supports the `arcade` mode of the game.\n- Using the `--verbose` flag will enable the verbose logging configuration.\n```\npython main.py play --mode=arcade --verbose\n```\n- It will take 5-10 minutes to load the word embedding model\n- Start the `arcade` version (in `blue` color theme) of the game in a full screen mode\n- Put the cursor in the game input field for the system to enter the suggestions\n- Wait for the ~~magic~~ model to load :tada:\n\n---\n\n#### Arcade mode\n\n[![Alt text](https://img.youtube.com/vi/E8QSteLOuns/0.jpg)](https://www.youtube.com/watch?v=E8QSteLOuns)\n\n---\n[Pravendra Singh](https://hackpravj.com)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpravj%2Fsemantris-solver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpravj%2Fsemantris-solver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpravj%2Fsemantris-solver/lists"}