{"id":19521490,"url":"https://github.com/curiousily/tweetcrafter","last_synced_at":"2025-10-27T05:09:47.062Z","repository":{"id":241725857,"uuid":"807506425","full_name":"curiousily/tweetcrafter","owner":"curiousily","description":"Write tweets with AI Agents (CrewAI) and LLMs (Llama 3, GPT-4o)","archived":false,"fork":false,"pushed_at":"2024-06-01T12:25:47.000Z","size":439,"stargazers_count":30,"open_issues_count":0,"forks_count":9,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-10-23T19:39:31.171Z","etag":null,"topics":["ai-agents","chatgpt","crewai","gpt-4o","langchain","llama","tweeter"],"latest_commit_sha":null,"homepage":"https://www.mlexpert.io/bootcamp/ai-agents-in-action","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/curiousily.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-29T08:26:56.000Z","updated_at":"2025-10-16T10:32:51.000Z","dependencies_parsed_at":"2024-08-03T07:51:11.115Z","dependency_job_id":"2c0d3486-7907-4e14-8e16-167bd86f854f","html_url":"https://github.com/curiousily/tweetcrafter","commit_stats":{"total_commits":8,"total_committers":1,"mean_commits":8.0,"dds":0.0,"last_synced_commit":"af6040f60a43ac8c4fe3d4ce7d1d939390d9517b"},"previous_names":["curiousily/tweetcrafter"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/curiousily/tweetcrafter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/curiousily%2Ftweetcrafter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/curiousily%2Ftweetcrafter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/curiousily%2Ftweetcrafter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/curiousily%2Ftweetcrafter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/curiousily","download_url":"https://codeload.github.com/curiousily/tweetcrafter/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/curiousily%2Ftweetcrafter/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281170198,"owners_count":26455518,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-26T02:00:06.575Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["ai-agents","chatgpt","crewai","gpt-4o","langchain","llama","tweeter"],"created_at":"2024-11-11T00:32:49.313Z","updated_at":"2025-10-27T05:09:47.046Z","avatar_url":"https://github.com/curiousily.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TweetCrafter\n\nWrite tweets with AI Agents (CrewAI)\n\n\u003ca href=\"https://www.mlexpert.io/bootcamp\" target=\"_blank\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/curiousily/tweetcrafter/master/.github/tweetcrafter.png\"\u003e\n\u003c/a\u003e\n\n## Installation\n\nClone the repo\n\n```sh\ngit clone git@github.com:curiousily/tweetcrafter.git\ncd tweetcrafter\n```\n\n```sh\npoetry install\n```\n\nInstall iPython kernel:\n\n```sh\npoetry run python -m ipykernel install --user --name tweetcrafter --display-name \"Python (tweetcrafter)\"\n```\n\n## Add API keys\n\nCreate a `.env` file in the root of the project and add your Groq and/or OpenAI API keys:\n\n```sh\nGROQ_API_KEY=\u003cGROQ_API_KEY\u003e\nOPENAI_API_KEY=\u003cOPENAI_API_KEY\u003e\n```\n\n## Usage\n\nGo to `app.py` and change the inputs:\n\n```py\ninputs = {\n    \"topic\": \"Summary of the key new features of Phi-3\",\n    \"urls\": [\n        \"https://huggingface.co/microsoft/Phi-3-vision-128k-instruct\",\n    ],\n    \"suggestion\": \"Focus on the performance and how-to use the model.\",\n}\n```\n\nAdd tweets to analyze their writing style in `data/tweets.md`:\n\n```md\n# Tweet\n\nEver wondered how to reproduce GPT-2 (124M) efficiently?\n@karpathy with llm.c has the answer!\n\n- 90 mins, $20 on 8X A100 80GB SXM\n- FineWeb dataset: 10B tokens\n- MFU: 49-60%, 178K tokens/sec\n\nhttps://github.com/karpathy/llm.c/discussions/481\n```\n\nRun the app:\n\n```sh\npoetry run python app.py\n```\n\n```py\n{\n   \"total_tokens\":12334,\n   \"prompt_tokens\":10260,\n   \"completion_tokens\":2074,\n   \"successful_requests\":8\n}\n```\n\n## Result\n\nThe tweets I got from the crew (saved to `output/tweet.md`):\n\n```md\nOriginal Tweet:\n\"Meet Phi-3, the cutting-edge AI model revolutionizing NLP! 🚀💻\n• Processes human language efficiently and accurately\n• Ideal for NLP, text gen, conversational AI, sentiment analysis, and language translation\n• Transparent, accountable, and fair decision-making\n• Trained on diverse datasets and compatible with TensorFlow and PyTorch\n#Phi3 #AI #NLP #LanguageModel #ResponsibleAI\n\nVersion 1:\n\"Unlock the power of Phi-3, the AI model that's changing the NLP game! 🚀💻\n• Efficient and accurate language processing\n• Perfect for text gen, conversational AI, sentiment analysis, and language translation\n• Transparency, accountability, and fairness in decision-making\n• Compatible with TensorFlow and PyTorch\n#Phi3 #AI #NLP #LanguageModel #ResponsibleAI\n\nVersion 2:\n\"Take your NLP projects to the next level with Phi-3! 🚀💻\n• Fast and accurate language processing\n• Ideal for conversational AI, sentiment analysis, and language translation\n• Built with transparency, accountability, and fairness in mind\n• Compatible with TensorFlow and PyTorch\n#Phi3 #AI #NLP #LanguageModel #ResponsibleAI\n\nVersion 3:\n\"Discover the future of NLP with Phi-3! 🚀💻\n• Efficient language processing for text gen, conversational AI, and more\n• Transparent, accountable, and fair decision-making\n• Trained on diverse datasets and compatible with TensorFlow and PyTorch\n• Revolutionize your NLP projects with Phi-3\n#Phi3 #AI #NLP #LanguageModel #ResponsibleAI\n```\n\n## Observability\n\n_TweetCrafter_ stores logs of prompts and individual agent logs in the `logs` directory.\n\nHave a look at the `notebooks/explore-logs.ipynb` notebook to explore the logs.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcuriousily%2Ftweetcrafter","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcuriousily%2Ftweetcrafter","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcuriousily%2Ftweetcrafter/lists"}