{"id":14964910,"url":"https://github.com/radames/llm-automator","last_synced_at":"2025-10-25T10:30:47.304Z","repository":{"id":218017368,"uuid":"745227198","full_name":"radames/LLM-automator","owner":"radames","description":"Create keyboard shortcuts for an LLM using OpenAI GPT, Ollama, HuggingFace with Automator on macOS.","archived":false,"fork":false,"pushed_at":"2024-03-06T01:02:09.000Z","size":897,"stargazers_count":146,"open_issues_count":1,"forks_count":13,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-02-07T11:49:07.319Z","etag":null,"topics":["automator","huggingface","llm","ollama","osx"],"latest_commit_sha":null,"homepage":"","language":"Python","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/radames.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,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2024-01-18T22:15:09.000Z","updated_at":"2025-02-06T08:10:21.000Z","dependencies_parsed_at":"2024-01-19T10:07:06.345Z","dependency_job_id":"54b361c7-b422-468c-8378-b2ccf051fca5","html_url":"https://github.com/radames/LLM-automator","commit_stats":null,"previous_names":["radames/llm-automator"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radames%2FLLM-automator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radames%2FLLM-automator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radames%2FLLM-automator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/radames%2FLLM-automator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/radames","download_url":"https://codeload.github.com/radames/LLM-automator/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238120382,"owners_count":19419763,"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","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":["automator","huggingface","llm","ollama","osx"],"created_at":"2024-09-24T13:33:57.487Z","updated_at":"2025-10-25T10:30:46.915Z","avatar_url":"https://github.com/radames.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM-automator\n\n## Guides\n[Huggingface-Backend](#huggingface-backend)  \n[Ollama](#ollama-backend)  \n[OpenAI](#openai)  \n\nFor a multi-platform solution, consider [plock project](https://github.com/jasonjmcghee/plock)\n\n# Huggingface Backend\n\n## Installation\n\nGet `HF_TOKEN` from \u003chttps://huggingface.co/settings/tokens\u003e\n\nEdit `llm-automator.workflow` with the Automator app, replace `HF_TOKEN` with your token.\n\nYou may also edit `MODEL=\"mistralai/Mixtral-8x7B-Instruct-v0.1\"` to use a different LLM from [huggingface.co/models](https://huggingface.co/models?pipeline_tag=text-generation\u0026other=endpoints_compatible\u0026sort=trending)\n\n\u003cimg src=\"assets/step-1.jpg\" style=\"max-width: 600px;\" /\u003e\n\n\u003cimg src=\"assets/step-2.jpg\" style=\"max-width: 600px;\" /\u003e\n\nInstall the workflow. This essentially copies the workflow to `~/Library/Services/llm-automator.workflow`.\n\n\u003cimg src=\"assets/step-3.jpg\" style=\"max-width: 600px;\" /\u003e\n\n\u003cimg src=\"assets/step-4.jpg\" style=\"max-width: 600px;\" /\u003e\n\nGo to System Preferences -\u003e Keyboard -\u003e Shortcuts -\u003e Services -\u003e General -\u003e llm-automator, and set the shortcut to whatever you want, in my case I set it to `⌃⌥⌘M`.\n\n\u003cimg src=\"assets/step-5.jpg\" style=\"max-width: 600px;\" /\u003e\n\n\u003cimg src=\"assets/step-6.jpg\" style=\"max-width: 600px;\" /\u003e\n\n## Usage\n\nIn any OSX application, select some text, and press the shortcut you set in step 3. The selected text will be replaced with the generated text from the model.\n\n# Ollama Backend\n\nInstall [ollama](https://ollama.ai/)\n\nRun in the background:\n\n```bash\nollama run mistral\n```\n\nInstall `llm-automator-ollama.workflow` the same way as above, no need to edit and add token, however you may edit `MODEL=\"mistral\"`, in case you want to use a different model\n\n\u003cimg src=\"assets/step-7.jpg\" width=\"270\"/\u003e\n\n\n## Vision\n\n\n\nhttps://github.com/radames/LLM-automator/assets/102277/d3336837-2b3d-471d-8c04-47e572cec411\n\n\n\n\n# OpenAI\n\n\nInstall `llm-automator-openai.workflow` the same way as above, however you may edit `OPENAI_KEY = \"sk-..........\"` and `MODEL = \"gpt-4-1106-preview\"`, in case you want to use a different model\n\n\u003cimg width=\"270\" alt=\"image\" src=\"https://github.com/radames/LLM-automator/assets/102277/47b8c108-72ed-4e3d-ab0e-fc10a1374858\"\u003e\n\n----\nhttps://github.com/radames/LLM-automator/assets/102277/5144a46d-7b3c-443e-a86e-c0b8205085f1\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fradames%2Fllm-automator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fradames%2Fllm-automator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fradames%2Fllm-automator/lists"}