{"id":13601608,"url":"https://github.com/abi/secret-llama","last_synced_at":"2025-10-04T19:49:42.133Z","repository":{"id":237997501,"uuid":"794304370","full_name":"abi/secret-llama","owner":"abi","description":"Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.","archived":false,"fork":false,"pushed_at":"2024-06-05T02:04:17.000Z","size":369,"stargazers_count":2608,"open_issues_count":24,"forks_count":164,"subscribers_count":20,"default_branch":"main","last_synced_at":"2025-04-14T11:11:51.332Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://secretllama.com","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/abi.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":["abi"]}},"created_at":"2024-04-30T21:24:56.000Z","updated_at":"2025-04-14T10:44:42.000Z","dependencies_parsed_at":"2024-05-03T21:45:03.897Z","dependency_job_id":"31cba08c-aacf-4323-b05c-acd90002bb8f","html_url":"https://github.com/abi/secret-llama","commit_stats":{"total_commits":68,"total_committers":3,"mean_commits":"22.666666666666668","dds":0.1029411764705882,"last_synced_commit":"5b197cd6420460b5d8c48de08f1774151b458ea1"},"previous_names":["abi/fully-private-chat","abi/secret-llama"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abi%2Fsecret-llama","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abi%2Fsecret-llama/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abi%2Fsecret-llama/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/abi%2Fsecret-llama/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/abi","download_url":"https://codeload.github.com/abi/secret-llama/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254292040,"owners_count":22046426,"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":"2024-08-01T18:01:05.246Z","updated_at":"2025-10-04T19:49:42.076Z","avatar_url":"https://github.com/abi.png","language":"TypeScript","funding_links":["https://github.com/sponsors/abi"],"categories":["TypeScript","others","Repos"],"sub_categories":[],"readme":"# Secret Llama\n\n![secret llama](https://github.com/abi/secret-llama/assets/23818/0bf43a95-4fe5-4c53-87bc-b558e5c4968f)\n\nEntirely-in-browser, fully private LLM chatbot supporting Llama 3, Mistral and other open source models. \n\n- Fully private = No conversation data ever leaves your computer\n- Runs in the browser = No server needed and no install needed!\n- Works offline\n- Easy-to-use interface on par with ChatGPT, but for open source LLMs\n\nBig thanks to the inference engine provided by [webllm](https://github.com/mlc-ai/web-llm).\n\nJoin us on Discord\n\n[![](https://dcbadge.vercel.app/api/server/QkVzykMc9V)](https://discord.gg/QkVzykMc9V)\n\nhttps://discord.gg/QkVzykMc9V\n\n## System Requirements\n\nTo run this, you need a modern browser with support for WebGPU. According to [caniuse](https://caniuse.com/?search=WebGPU), WebGPU is supported on:\n\n- Google Chrome\n- Microsoft Edge\n\nIt's also available in Firefox, but it needs to be enabled manually through the dom.webgpu.enabled flag. Safari on MacOS also has experimental support for WebGPU which can be enabled through the WebGPU experimental feature. \n\nIn addition to WebGPU support, various models might have specific RAM requirements.\n\n## Try it out\n\nYou can [try it here](https://secretllama.com).\n\nTo compile the React code yourself, download the repo and then, run\n\n```\nyarn\nyarn build-and-preview\n```\n\nIf you're looking to make changes, run the development environment with live reload:\n\n```\nyarn\nyarn dev\n```\n\n## Supported models\n\n| Model                     | Model Size |\n|---------------------------|------------|\n| TinyLlama-1.1B-Chat-v0.4-q4f32_1-1k | 600MB      |\n| Llama-3-8B-Instruct-q4f16_1 ⭐         | 4.3GB      |\n| Phi1.5-q4f16_1-1k                   | 1.2GB        |\n| Mistral-7B-Instruct-v0.2-q4f16_1 ⭐    | 4GB        |\n\n\n## Looking for contributors\n\nWe would love contributions to improve the interface, support more models, speed up initial model loading time and fix bugs.\n\n## Other Projects by Author\n\nCheck out [screenshot to code](https://github.com/abi/screenshot-to-code) and [Pico - AI-powered app builder](https://picoapps.xyz)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabi%2Fsecret-llama","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabi%2Fsecret-llama","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabi%2Fsecret-llama/lists"}