{"id":26037563,"url":"https://github.com/explicit-logic/light-ai","last_synced_at":"2025-10-06T13:14:45.860Z","repository":{"id":270207491,"uuid":"909636013","full_name":"explicit-logic/light-ai","owner":"explicit-logic","description":"Easy to use single-file executable to run LLMs locally on your machine","archived":false,"fork":false,"pushed_at":"2025-01-19T04:44:20.000Z","size":362,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-14T08:55:34.490Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/explicit-logic.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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},"funding":{"github":null,"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":"b_andrianov","thanks_dev":null,"custom":null}},"created_at":"2024-12-29T10:31:36.000Z","updated_at":"2025-01-04T05:04:13.000Z","dependencies_parsed_at":"2024-12-29T11:38:23.167Z","dependency_job_id":null,"html_url":"https://github.com/explicit-logic/light-ai","commit_stats":null,"previous_names":["explicit-logic/light-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/explicit-logic/light-ai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explicit-logic%2Flight-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explicit-logic%2Flight-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explicit-logic%2Flight-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explicit-logic%2Flight-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/explicit-logic","download_url":"https://codeload.github.com/explicit-logic/light-ai/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/explicit-logic%2Flight-ai/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278615630,"owners_count":26016211,"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":"2025-10-06T02:00:05.630Z","response_time":65,"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":[],"created_at":"2025-03-07T08:19:05.071Z","updated_at":"2025-10-06T13:14:45.833Z","avatar_url":"https://github.com/explicit-logic.png","language":"TypeScript","funding_links":["https://buymeacoffee.com/b_andrianov"],"categories":[],"sub_categories":[],"readme":"Light AI\n========\nEasy to use single-file executable to run LLMs locally on your machine\n\n![Demo](demo.gif)\n\n## Getting Started\n\n- **Download the right Light AI server for your operating system.**\n\n1. Run `./light-ai` (`./light-ai.exe` for Windows) from the command line.\n2. Open Swagger (`http://0.0.0.0:8000/swagger`) and pick `id` of one of the available models: `GET /v1/models`.\n3. Restart the server with the model `id` in params (For example: `./light-ai -m llama3.2-1b-instruct`).\n\nThat's it! Your personal AI server is ready for usage. Try `POST /v1/ask` and `POST /v1/completion` to check.\n\n## Download\n\n\u003ctable\u003e\n  \u003ctr style=\"text-align:center\"\u003e\n    \u003ctd style=\"text-align:center\"\u003e\u003cb\u003eMacOS Silicon\u003c/b\u003e\u003c/td\u003e\n    \u003ctd style=\"text-align:center\"\u003e\n      \u003ca href='https://github.com/explicit-logic/light-ai/releases/download/v0.0.1/light-ai-mac-silicon' download=\"light-ai\"\u003e\n        \u003cb\u003elight-ai\u003c/b\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr style=\"text-align:center\"\u003e\n    \u003ctd style=\"text-align:center\"\u003e\u003cb\u003eMacOS Intel\u003c/b\u003e\u003c/td\u003e\n    \u003ctd style=\"text-align:center\"\u003e\n      \u003ca href='https://github.com/explicit-logic/light-ai/releases/download/v0.0.1/light-ai-mac-intel' download=\"light-ai\"\u003e\n        \u003cb\u003elight-ai\u003c/b\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr style=\"text-align:center\"\u003e\n    \u003ctd style=\"text-align:center\"\u003e\u003cb\u003eLinux\u003c/b\u003e\u003c/td\u003e\n    \u003ctd style=\"text-align:center\"\u003e\n      \u003ca href='https://github.com/explicit-logic/light-ai/releases/download/v0.0.1/light-ai-linux' download=\"light-ai\"\u003e\n        \u003cb\u003elight-ai\u003c/b\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n   \u003ctr style=\"text-align:center\"\u003e\n    \u003ctd style=\"text-align:center\"\u003e\u003cb\u003eWindows\u003c/b\u003e\u003c/td\u003e\n    \u003ctd style=\"text-align:center\"\u003e\n      \u003ca href='https://github.com/explicit-logic/light-ai/releases/download/v0.0.1/light-ai-win.exe' download=\"light-ai.exe\"\u003e\n        \u003cb\u003elight-ai.exe\u003c/b\u003e\n      \u003c/a\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n## Usage\n\n```sh\n./light-ai -p 8000 -m llama3.2-1b-instruct\n```\n\n| Argument | Explanation |\n| -------- | ----------- |\n| `-p, --port` | Port to listen on (__Optional__) |\n| `-m, --model` | Model name (__Optional__) |\n\n## API Endpoints\n\n### POST `/v1/ask`: Get a quick reply for a given `prompt`\n\n*Options:*\n\n`prompt`: Provide the prompt to get a reply (__Required__)\n\n`model`: Model name (__Optional__)\n\n`grammar`: Set grammar for grammar-based sampling (__Optional__)\n\n`schema`: JSON response with a schema (__Optional__)\n\n\nFor Example:\n\n```sh\ncurl http://0.0.0.0:8000/v1/ask --header 'Content-Type: application/json' --data '{\"prompt\": \"Is an apple more expensive than a banana?\"}'\n```\n\n### POST `/v1/completion`: Given a `prompt`, it returns the predicted completion.\n\n*Options:*\n\n`prompt`: Provide the prompt for this completion as a string (__Required__)\n\n`model`: Model name (__Optional__)\n\nFor Example:\n\n```sh\ncurl http://0.0.0.0:8000/v1/completion --header 'Content-Type: application/json' --data '{\"prompt\": \"Here is a list of sweet fruits:\"}'\n```\n\n### GET `/v1/models`: List of models\n\n### POST `/v1/models/pull`: Pull a model\n\n*Options:*\n\n`model`: Model name (__Required__)\n\n## Acknowledgements\n* Bun: [oven-sh/bun](https://github.com/oven-sh/bun)\n* node-llama-cpp: [withcatai/node-llama-cpp](https://github.com/withcatai/node-llama-cpp)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexplicit-logic%2Flight-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fexplicit-logic%2Flight-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fexplicit-logic%2Flight-ai/lists"}