{"id":15165952,"url":"https://github.com/simonbogaerts/bogsi.ceridwen","last_synced_at":"2026-02-09T19:31:30.432Z","repository":{"id":254431595,"uuid":"846059537","full_name":"simonbogaerts/Bogsi.Ceridwen","owner":"simonbogaerts","description":"A small experiment with docker, dev containers and a LLM. An experiment, but quiet useful. Ceridwen is a personal assistant that can be run on the GPU.","archived":false,"fork":false,"pushed_at":"2024-08-23T11:27:12.000Z","size":18,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-08T16:54:02.170Z","etag":null,"topics":["devcontainers","docker","docker-compose","llms","ollama"],"latest_commit_sha":null,"homepage":"","language":"C#","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/simonbogaerts.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,"publiccode":null,"codemeta":null}},"created_at":"2024-08-22T13:04:51.000Z","updated_at":"2024-08-23T20:39:35.000Z","dependencies_parsed_at":"2024-08-23T12:42:51.359Z","dependency_job_id":"a54c9ccf-e51f-47f3-823d-e9bf6c6fc9ac","html_url":"https://github.com/simonbogaerts/Bogsi.Ceridwen","commit_stats":null,"previous_names":["simonbogaerts/bogsi.ceridwen"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/simonbogaerts/Bogsi.Ceridwen","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonbogaerts%2FBogsi.Ceridwen","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonbogaerts%2FBogsi.Ceridwen/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonbogaerts%2FBogsi.Ceridwen/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonbogaerts%2FBogsi.Ceridwen/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/simonbogaerts","download_url":"https://codeload.github.com/simonbogaerts/Bogsi.Ceridwen/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/simonbogaerts%2FBogsi.Ceridwen/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266854692,"owners_count":23995488,"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":"2025-07-24T02:00:09.469Z","response_time":99,"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":["devcontainers","docker","docker-compose","llms","ollama"],"created_at":"2024-09-27T04:21:04.302Z","updated_at":"2026-02-09T19:31:30.374Z","avatar_url":"https://github.com/simonbogaerts.png","language":"C#","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Ceridwen by BOGsi \n\nCeridwen, a figure from Welsh mythology, said to be the keeper of the cauldron of knowledge, mother of transformation and the white lady of inspiration and death.\n\n\n# What is Ceridwen?\n\nAn simple application that will run a Large Language Model (LLM) on your local machine, utilizing your GPU (preferably). \n\nThe application itself is a basic dotnet console application that will pass on your questions to an Ollama model by Meta. \n\nThis was inteded as an experiment while learning docker/docker-compose/devcontainers. Not sure if further updates will be made to the repo. \n\n\n# Prerequisites \n\n* Docker\n* WSL2+\n\nIf usisng the GPU:\n\n* Nvidia GPU\n* up-to-date GPU drivers \n\n\n# How to run Ceridwen\n\nSimply use the following command in the terminal (when in the main project folder):\n\n```\ndocker compose up -d\n```\n\nAfterwards attach to the running console application and get on typing. \n\n```\ndocker attach \u003ccontainer_name_or_id\u003e\n```\n\nTo stop Ceridwen ctrl + C out of the attached window and use the following docker command.\n\n```\ndocker compose down\n```\n\n## Notes \n\n* Cerdiwen can be run on the CPU instead of the GPU by commenting out the deploy section in the docker-compose.yml, however this will vastly decrease the time required for it to handle the prompts and make it far less useable as a tool. \n* By default llama3 model is used, adjust the environment variable in the docker compose if you want to use a larger/newer model. \n\n\n\n# Resources \n\nResources used to create this tiny project include: \n\n* **Ollama**. https://hub.docker.com/r/ollama/ollama\n* **OllamaSharp**. https://github.com/awaescher/OllamaSharp\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimonbogaerts%2Fbogsi.ceridwen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsimonbogaerts%2Fbogsi.ceridwen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimonbogaerts%2Fbogsi.ceridwen/lists"}