{"id":13593690,"url":"https://github.com/danielgross/localpilot","last_synced_at":"2025-05-15T03:02:51.265Z","repository":{"id":197798143,"uuid":"699093133","full_name":"danielgross/localpilot","owner":"danielgross","description":null,"archived":false,"fork":false,"pushed_at":"2024-02-25T18:19:04.000Z","size":33,"stargazers_count":3376,"open_issues_count":25,"forks_count":147,"subscribers_count":26,"default_branch":"main","last_synced_at":"2025-04-14T00:59:01.145Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/danielgross.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":"2023-10-01T22:20:04.000Z","updated_at":"2025-04-13T22:10:51.000Z","dependencies_parsed_at":"2024-11-06T15:51:34.145Z","dependency_job_id":null,"html_url":"https://github.com/danielgross/localpilot","commit_stats":null,"previous_names":["danielgross/localpilot"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgross%2Flocalpilot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgross%2Flocalpilot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgross%2Flocalpilot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielgross%2Flocalpilot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/danielgross","download_url":"https://codeload.github.com/danielgross/localpilot/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254264737,"owners_count":22041789,"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":[],"created_at":"2024-08-01T16:01:23.186Z","updated_at":"2025-05-15T03:02:51.203Z","avatar_url":"https://github.com/danielgross.png","language":"Python","readme":"# localpilot\n_Use GitHub Copilot locally on your Macbook with one-click!_\n\n![image](https://github.com/danielgross/localpilot/assets/279531/521d0613-7423-4839-a5e8-42098cd65a5e)\n\n## Demo Video\n\n\nhttps://github.com/danielgross/localpilot/assets/279531/3259981b-39f7-4bfa-8a45-84bde6d4ba4c\n\n\n\n_This video is not sped up or slowed down._\n\n## Installation \n1. First, open VS Code Settings and add the following to your settings.json file: \n```json\n\"github.copilot.advanced\": {\n    \"debug.testOverrideProxyUrl\": \"http://localhost:5001\",\n    \"debug.overrideProxyUrl\": \"http://localhost:5001\"\n}\n```\n\n2. Create a virtualenv to run this Python process, install the requirements, and download the models. \n```python\nvirtualenv venv\nsource venv/bin/activate\npip install -r requirements.txt\n# First setup run. This will download several models to your ~/models folder.\npython app.py --setup \n``` \n\n3. Run it! \n```python\npython app.py\n```\n\nEnjoy your on-device Copilot! \n\n## Caveat FAQ\n\n**Is the code as good as GitHub Copilot?** \n\nFor simple line completions yes. For simple function completions, mostly. For complex functions... maybe. \n\n**Is it as fast as GitHub Copilot?**\n\nOn my Macbook Pro with an Apple M2 Max, the 7b models are roughly as fast. The 34b models are not. Please consider this repo a demonstration of a very inefficient implementation. I'm sure we can make it faster; please do submit a pull request if you'd like to help. For example, I think we need debouncer because sometimes llama.cpp/GGML isn't fast at interrupting itself when a newer request comes in.\n\n**Can this be packaged as a simple Mac app?**\n\nYes!, I'm sure it can be, I just haven't had the time. Please do submit a pull request if you're into that sort of thing!\n\n**Should there be a meta-model that routes to a 1b for autocomplete, 7b for more complex autocomplete, and a 34b for program completion?**\n\nHmm, that seems like an interesting idea.\n\n**OK, but in summary, is it good?** \n\nOnly if your network is bad. I don't think it's competitive if you have fast Internet. But it sure is awesome on airplanes and while tethering!\n\n\n","funding_links":[],"categories":["others","Python","Artificial Intelligence"],"sub_categories":["Android Launcher"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielgross%2Flocalpilot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdanielgross%2Flocalpilot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielgross%2Flocalpilot/lists"}