{"id":13432427,"url":"https://github.com/kwame-mintah/vscode-ollama-local-code-copilot","last_synced_at":"2025-10-18T04:29:22.183Z","repository":{"id":220234030,"uuid":"751066409","full_name":"kwame-mintah/vscode-ollama-local-code-copilot","owner":"kwame-mintah","description":"Run a local instance of a code-specialized model via Ollama and connect to your VSCode for code completion / generation.","archived":false,"fork":false,"pushed_at":"2024-07-09T21:06:14.000Z","size":25,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-10-27T11:52:01.923Z","etag":null,"topics":["codellama","docker","docker-compose","ollama","vscode"],"latest_commit_sha":null,"homepage":"","language":"Dockerfile","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/kwame-mintah.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":"2024-01-31T21:30:21.000Z","updated_at":"2024-08-19T08:49:54.000Z","dependencies_parsed_at":"2024-02-19T21:26:54.164Z","dependency_job_id":"8308f94d-7a3f-4127-b413-26ece075282d","html_url":"https://github.com/kwame-mintah/vscode-ollama-local-code-copilot","commit_stats":null,"previous_names":["kwame-mintah/vscode-ollama-local-code-copilot"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kwame-mintah%2Fvscode-ollama-local-code-copilot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kwame-mintah%2Fvscode-ollama-local-code-copilot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kwame-mintah%2Fvscode-ollama-local-code-copilot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kwame-mintah%2Fvscode-ollama-local-code-copilot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kwame-mintah","download_url":"https://codeload.github.com/kwame-mintah/vscode-ollama-local-code-copilot/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228363963,"owners_count":17908319,"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":["codellama","docker","docker-compose","ollama","vscode"],"created_at":"2024-07-31T02:01:11.453Z","updated_at":"2025-10-18T04:29:22.077Z","avatar_url":"https://github.com/kwame-mintah.png","language":"Dockerfile","funding_links":[],"categories":["Dockerfile"],"sub_categories":[],"readme":"# Visual Studio Code (VSCode) Ollama Local Code Co-pilot\n\nAn example to run an instance of [Ollama](https://ollama.ai/) via docker-compose and connect to VSCode for code completion / generation.\n\n## Prerequisites\n\nThe project uses the following software:\n* [Docker for desktop](https://www.docker.com/products/docker-desktop/)\n* [Llama Coder](https://marketplace.visualstudio.com/items?itemName=ex3ndr.llama-coder)\n\n## Usage\n\n1. Navigate to the directory where the repository has been cloned and start the containers:\n\n   ```commandline\n   docker-compose up -d --build\n   ```\n\n2. Wait for the `ollama-setup-1` service to complete downloading [codellama](https://ollama.ai/library/codellama)[^1] and other models.\n\n   ```commandline\n    2024-01-31 23:36:50 {\"status\":\"verifying sha256 digest\"}\n    2024-01-31 23:36:50 {\"status\":\"writing manifest\"}\n    2024-01-31 23:36:50 {\"status\":\"removing any unused layers\"}\n    2024-01-31 23:36:50 {\"status\":\"success\"}\n    100 1128k    0 1128k    0    21   2546      0 --:--:--  0:07:33 --:--:--    23\n   ```\n\n3. Install Llama Coder VSCode extension\n\n![Example of extension running for code completion](/docs/llama_coder_stable_code_running_output_example.gif)\n\n\u003e [!NOTE]\n\u003e Initial prompts to Ollama might be slow, if the model and/or container was not previously running and not interacted with recently.\n\u003e Please note that the [`.env.example`](.env.example) has the model loaded in memory set to [1 hour](https://github.com/ollama/ollama/blob/v0.5.11/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately).\n\n## Notes\n\n### Using different Large Language Models (LLM) with Llama Coder\n\nYou can edit the `docker-entrypoint.sh` to pull any model available in the [Ollama library](https://ollama.ai/library), however Llama Coder currently\nsupports a [few models](https://github.com/ex3ndr/llama-coder?tab=readme-ov-file#models) via the UI. Within the extension settings select a 'custom'\ninference model and then enter the model name within the \"Inference \u003e Custom: Model\" field.\n\n### What devices has this been tested on?\n\nI have only tried the container on my MacBook Pro M1 Pro with 16 RAM (2021), so YMMV. Also unable to comment on model(s) that require a\nGraphics processing unit (GPU).\n\n[^1]: Not all models perform the same on the host machine, please ensure you select an appropriate model for the best performance.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkwame-mintah%2Fvscode-ollama-local-code-copilot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkwame-mintah%2Fvscode-ollama-local-code-copilot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkwame-mintah%2Fvscode-ollama-local-code-copilot/lists"}