{"id":28042177,"url":"https://github.com/stanford-mast/blast","last_synced_at":"2025-05-11T14:04:59.892Z","repository":{"id":290615575,"uuid":"960724144","full_name":"stanford-mast/blast","owner":"stanford-mast","description":"Browser-LLM Auto-Scaling Technology","archived":false,"fork":false,"pushed_at":"2025-05-08T18:59:10.000Z","size":3388,"stargazers_count":487,"open_issues_count":4,"forks_count":17,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-05-08T19:46:08.777Z","etag":null,"topics":["ai-agents","browser-automation","llm-inference","python"],"latest_commit_sha":null,"homepage":"http://blastproject.org/","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/stanford-mast.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,"zenodo":null}},"created_at":"2025-04-05T00:03:34.000Z","updated_at":"2025-05-08T18:59:13.000Z","dependencies_parsed_at":"2025-04-29T18:59:16.046Z","dependency_job_id":null,"html_url":"https://github.com/stanford-mast/blast","commit_stats":null,"previous_names":["stanford-mast/blast"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stanford-mast%2Fblast","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stanford-mast%2Fblast/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stanford-mast%2Fblast/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stanford-mast%2Fblast/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/stanford-mast","download_url":"https://codeload.github.com/stanford-mast/blast/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253576267,"owners_count":21930169,"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":["ai-agents","browser-automation","llm-inference","python"],"created_at":"2025-05-11T14:02:21.707Z","updated_at":"2025-05-11T14:04:59.869Z","avatar_url":"https://github.com/stanford-mast.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"docs/assets/blast_icon_only.png\" width=\"200\" height=\"200\" alt=\"BLAST Logo\"\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\" style=\"font-size: 24px\"\u003eA high-performance serving engine for web browsing AI.\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n[![Website](https://img.shields.io/badge/blastproject.org-FFE067)](https://blastproject.org)\n[![Documentation](https://img.shields.io/badge/Docs-FFE067)](https://docs.blastproject.org)\n[![Discord](https://img.shields.io/badge/Discord-FFE067)](https://discord.gg/NqrkJwYYh4)\n[![Twitter Follow](https://img.shields.io/twitter/follow/realcalebwin?style=social)](https://x.com/realcalebwin)\n\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"website/assets/blast_ui_gif.gif\" alt=\"BLAST UI Demo\" width=\"80%\"\u003e\n\u003c/div\u003e\n\n## ❓ Use Cases\n\n1. **I want to add web browsing AI to my app...** BLAST serves web browsing AI with an OpenAI-compatible API and concurrency and streaming baked in.\n2. **I need to automate workflows...** BLAST will automatically cache and parallelize to keep costs down and enable interactive-level latencies.\n3. **Just want to use this locally...** BLAST makes sure you stay under budget and not hog your computer's memory.\n\n## 🚀 Quick Start\n\n```bash\npip install blastai \u0026\u0026 blastai serve\n```\n\n```python\nfrom openai import OpenAI\n\nclient = OpenAI(\n    api_key=\"not-needed\",\n    base_url=\"http://127.0.0.1:8000\"\n)\n\n# Stream real-time browser actions\nstream = client.responses.create(\n    model=\"not-needed\",\n    input=\"Compare fried chicken reviews for top 10 fast food restaurants\",\n    stream=True\n)\n\nfor event in stream:\n    if event.type == \"response.output_text.delta\":\n        print(event.delta if \" \" in event.delta else \"\u003cscreenshot\u003e\", end=\"\", flush=True)\n```\n\n## ✨ Features\n\n- 🔄 **OpenAI-Compatible API** Drop-in replacement for OpenAI's API\n- 🚄 **High Performance** Automatic parallelism and prefix caching\n- 📡 **Streaming** Stream browser-augmented LLM output to users\n- 📊 **Concurrency** Out-of-the-box support many users with efficient resource management\n\n## 📚 Documentation\n\nVisit [documentation](https://docs.blastproject.org) to learn more.\n\n## 🤝 Contributing\n\nAwesome! See our [Contributing Guide](https://docs.blastproject.org/development/contributing) for details.\n\n## 📄 MIT License\n\nAs it should be!","funding_links":[],"categories":["Projects and Implementations","🌐 Web Automation \u0026 Scraping"],"sub_categories":["🟩 Development Tools 🛠️"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstanford-mast%2Fblast","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstanford-mast%2Fblast","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstanford-mast%2Fblast/lists"}