{"id":13602351,"url":"https://github.com/pgibler/cmdh","last_synced_at":"2026-04-15T19:48:34.112Z","repository":{"id":155830908,"uuid":"629724377","full_name":"pgibler/cmdh","owner":"pgibler","description":"Create Linux commands from natural language, in the shell.","archived":false,"fork":false,"pushed_at":"2026-02-25T07:51:00.000Z","size":254,"stargazers_count":125,"open_issues_count":10,"forks_count":10,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-04-15T19:48:31.475Z","etag":null,"topics":["artificial-intelligence","automation","shell","typescript"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","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/pgibler.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-04-18T22:43:31.000Z","updated_at":"2026-04-10T01:56:58.000Z","dependencies_parsed_at":"2023-11-07T08:24:47.131Z","dependency_job_id":"5e0cd160-2c1f-46a2-8c59-d933fa9b35e1","html_url":"https://github.com/pgibler/cmdh","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pgibler/cmdh","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pgibler%2Fcmdh","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pgibler%2Fcmdh/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pgibler%2Fcmdh/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pgibler%2Fcmdh/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pgibler","download_url":"https://codeload.github.com/pgibler/cmdh/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pgibler%2Fcmdh/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31857625,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-15T15:24:51.572Z","status":"ssl_error","status_checked_at":"2026-04-15T15:24:39.138Z","response_time":63,"last_error":"SSL_read: 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":["artificial-intelligence","automation","shell","typescript"],"created_at":"2024-08-01T18:01:20.777Z","updated_at":"2026-04-15T19:48:34.088Z","avatar_url":"https://github.com/pgibler.png","language":"TypeScript","funding_links":[],"categories":["\u003cimg src=\"./assets/satellite.svg\" width=\"16\" height=\"16\" style=\"vertical-align: middle;\"\u003e Satellites","automation"],"sub_categories":[],"readme":"# cmdh - Generate Linux commands using an LLM\n\ncmdh (short for Command Helper) is a tool that invokes LLM models provided by ollama or OpenAI to convert a command request into a desired command.\n\nUse it to look up commands and flags that that you don't know offhand or generate complex commands with chaining.\n\n[cmdh_demonstration_video.webm](https://user-images.githubusercontent.com/119892/233747166-552339ef-f3fe-4eb5-9161-db574b6f96fc.webm)\n\n## Features\n\n- Generate Linux commands from natural language\n- Interactively run the commands using a hotkey menu system\n- Differentiates between shell command types: interactive and non-interactive\n- Supports [ChatGPT](https://platform.openai.com/docs/overview), [ollama](https://ollama.ai/), and [text-generation-webui](https://github.com/oobabooga/text-generation-webui)\n\n## Prerequisites\n\n- NodeJS - [installation guide](https://nodejs.org/en/download/package-manager)\n- npm - [installation guide](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm)\n- tsc - [installation guide](https://www.npmjs.com/package/typescript)\n\n## Installation\n\n1. Set up and configure cmdh using the following command:\n```\ngit clone https://github.com/pgibler/cmdh.git \u0026\u0026 cd cmdh \u0026\u0026 ./install.sh\n```\n2. Run it like so:\n```\ncmdh 'Output the number of lines of code committed to git last month'\n```\n3. Interact with the result interface to run the setup commands, desired command, all of the commands, or quit.\n\n**NOTE**: You will have to reload your .bashrc / .zshrc / etc. or open a new terminal to make the cmdh command available in the shell. In Debian / Ubuntu, this is done by running `source ~/.bashrc`.\n\n## Configuring\n\nBefore running cmdh, you will need to configure an LLM host and set configuration options required of that host.\n\n- Run `cmdh configure` to start the configuration wizard. You will be asked to select an LLM host and input settings required by that host.\n- Run `cmdh configure show` to display your current configuration.\n\n### OpenAI\n\n1. Generate an OpenAI key [here](https://platform.openai.com/api-keys).\n2. Run `cmdh configure` and select the OpenAI option.\n3. Select a model \u0026 input your OpenAI key.\n\n### ollama\n\n1. Install \u0026 run the ollama service \u0026 pull the codellama model using the following commands:\n```\ncurl https://ollama.ai/install.sh | sh\nollama pull codellama\n```\n2. Run `cmdh configure`, select the ollama option, and set 'codellama' as the model.\n\n### text-generation-webui\n\n1. Clone the repo: `git clone https://github.com/oobabooga/text-generation-webui`\n2. Navigate to the cloned text-generation-webui folder and start the server by running `./start_linux --api --listen`.\n3. Open the web UI for text-generation-webui (http://localhost:7860), open the \"Model\" tab, and in the \"Download model or LoRA\" form, input `Trelis/Llama-2-7b-chat-hf-function-calling-v2` and press \"Download\".\n4. Click the reload button next to the Model dropdown menu under the model tab \u0026 select `llama-2-7b-function-calling.Q3_K_M.gguf`. Then click \"Load\" to load the model.\n2. Run `cmdh configure` and choose the 'text-generation-webui' option.\n\ncmdh will automatically send the prompts to whichever model is loaded by text-generation-webui.\n\nHuggingFace model URL: [https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2)\n\n## Roadmap\n\nThe issue tracker is mostly feature requests I have put in so I don't forget them. If you have any bug reports or good ideas, please include them in the tracker.\n\n## Issues\n\nIf you run into any issues installing or running cmdh, please open a ticket in the project tracker. Include a detailed bug report with stacktraces and inputs and the mode of operation (OpenAI or ollama).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpgibler%2Fcmdh","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpgibler%2Fcmdh","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpgibler%2Fcmdh/lists"}