{"id":24612676,"url":"https://github.com/souze-san/webllm-bot","last_synced_at":"2026-02-11T17:02:01.762Z","repository":{"id":271852531,"uuid":"914569904","full_name":"SouZe-San/webllm-bot","owner":"SouZe-San","description":"Lightweight Conversational AI running on WebGPU","archived":false,"fork":false,"pushed_at":"2025-01-10T10:05:11.000Z","size":405,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-05-06T21:50:05.053Z","etag":null,"topics":["llm","slm","svelte","webgpu","webllm"],"latest_commit_sha":null,"homepage":"","language":"Svelte","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/SouZe-San.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":"2025-01-09T21:20:33.000Z","updated_at":"2025-01-10T10:05:14.000Z","dependencies_parsed_at":"2025-01-10T10:43:46.058Z","dependency_job_id":null,"html_url":"https://github.com/SouZe-San/webllm-bot","commit_stats":null,"previous_names":["souze-san/webllm-bot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SouZe-San/webllm-bot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SouZe-San%2Fwebllm-bot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SouZe-San%2Fwebllm-bot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SouZe-San%2Fwebllm-bot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SouZe-San%2Fwebllm-bot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SouZe-San","download_url":"https://codeload.github.com/SouZe-San/webllm-bot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SouZe-San%2Fwebllm-bot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29338663,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-11T16:14:43.024Z","status":"ssl_error","status_checked_at":"2026-02-11T16:14:15.258Z","response_time":97,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["llm","slm","svelte","webgpu","webllm"],"created_at":"2025-01-24T20:24:37.139Z","updated_at":"2026-02-11T17:02:01.743Z","avatar_url":"https://github.com/SouZe-San.png","language":"Svelte","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Lightweight Conversational AI with WebGPU \n\nThis project demonstrates an innovative architecture for deploying lightweight, optimized large language models (LLMs) in web applications. By leveraging the WebGPU web API, the solution enables efficient inference on client-side devices, promoting energy efficiency and sustainability in conversational AI. This demo is created for ICCRET 2025 paper submission.\n\n## Features\n\n- **Client-Side Inference**: Utilizes WebGPU API for running models directly in the browser.\n- **Optimized Model**: Uses the Qwen2.5-0.5B-Instruct-q4f16_1-MLC model.\n- **User-Friendly Interface**: Built with Svelte.js for a responsive and intuitive user experience.\n\n## Installation\n\nTo get started with this project, clone the repository and install the necessary dependencies:\n\n```bash\ngit clone https://github.com/SouZe-San/webllm-bot.git\ncd webllm-bot\nbun install\n```\n\n## Usage\n\nRun the application locally:\n\n```bash\nbun run dev\n```\n\nOpen your browser and navigate to `http://localhost:5173` to access the demo customer support site and the chatbot.\n\n## Acknowledgements\n\nWe would like to thank the teams behind the [WebLLM](https://github.com/mlc-ai/web-llm) JavaScript Library, which facilitated the integration of pre-compiled models and loading to WebGPU.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsouze-san%2Fwebllm-bot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsouze-san%2Fwebllm-bot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsouze-san%2Fwebllm-bot/lists"}