Vision-grounding plugin for browser-use agents with SoM, Florence-2, Vision–DOM alignment, adaptive visual context, and objective evaluation.
☆104Jun 26, 2026Updated 2 weeks ago
Alternatives and similar repositories for browser-use-vision
Users that are interested in browser-use-vision are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- AICodePilot is an AI codebase understanding and development assistance system based on LLM Agents, designed for programmers. It supports …☆51Jun 18, 2026Updated 3 weeks ago
- Reference implementation and reproducibility artifact for the TOKI paper (PVLDB Vol 20 / VLDB 2027): a bitemporal operator algebra for co…☆52May 26, 2026Updated last month
- Consistency in Diffusion-Based Visual Generation: A Survey☆236Jun 16, 2026Updated 3 weeks ago
- Open-source AI Agent platform with React/TSX & HTML plugin dev modes. Built-in 60+ APIs, multi-project, MCP tools, sandbox engine. Offici…☆41Jul 2, 2026Updated last week
- No.0 — AI Agent Safety Guardian (cognitive-file monitor + internal control DLC)☆97May 10, 2026Updated 2 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- FREE version of Typeless/Wisper/Monologue/闪电说 - no word limit, no subscription☆118Jun 21, 2026Updated 3 weeks ago
- Sequence-derived peptide property profiling and early-stage developability scoring.☆84Jun 21, 2026Updated 3 weeks ago
- Vibe-Nothing-UI-Design — a zero-dependency, Nothing-inspired UI design system for the web (monochrome, round-dot type & icons, signal-red…☆141Jun 15, 2026Updated 3 weeks ago
- 1688 商品全方位分析诊断工具，整合多个数据源对指定商品进行深度分析。当用户需要分析某个指定商品表现、诊断流量问题、优化商品策略时使用。适用于指定商品的：商品数据分析、销售表现诊断、搜索排名问题分析、广告效果评估、市场竞争分析、商品优化建议。触发关键词包括"分析这个商品"…☆100May 13, 2026Updated 2 months ago
- ☆108May 13, 2026Updated 2 months ago
- Systematizing Unified Multimodal In-Context Learning through a Capability-Oriented Taxonomy☆54Jul 3, 2026Updated last week
- ACOT-VLA-WM is an advanced Vision-Language-Action robotics framework that uses a predictive world model to generate visual subgoals, impr…☆103Jun 5, 2026Updated last month
- ☆93Jun 8, 2026Updated last month
- 🎬 哔哩哔哩视频转文档 | Claude Code Skill: 自动将B站视频AI字幕提取为结构化Markdown文档☆103Jul 3, 2026Updated last week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Try Targie — native macOS app that finds duplicate and visually similar videos & images. Free & open source.☆103Updated this week
- 408 考研四科可视化平台 - 数据结构/组成原理/操作系统/计算机网络的算法动画演示☆106Jun 5, 2026Updated last month
- 1688采购询盘寻源能力。当用户有模糊的采购需求但尚未选定具体商品时，通过描述商品名称、数量和需求，发起采购询盘任务，由平台匹配合适的供应商和报价方案。 核心定位：采购前的询盘寻源阶段，帮助用户将模糊的采购意向转化为结构化询盘，获取供应商报价。 触发词：询盘、询价、寻源、采…☆107May 6, 2026Updated 2 months ago
- 1688营销 Skill —— 帮助商家进行招商活动报名、查看商机推荐等营销操作。 核心工具能力：招商活动查询、商品建议价查询、活动报名提交、商机推荐查询。 触发词：报名活动、招商活动、查询活动、提报、报名、活动报名、查看建议价、商机推荐、商机、市场机会、找商机、查商机，不…☆100May 6, 2026Updated 2 months ago
- A macOS Dynamic Island for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, hooks, skills, and local agent management.☆184Jul 7, 2026Updated last week
- 1688 分销唯一主入口。选品铺货、订单管理、知识库查询、店铺绑定，涵盖分销全链路。当用户提到铺货、选品、分销、上架、查订单、催发、旺旺、发货流程、绑店时触发。不要在用户仅询问非1688业务（如闲聊、天气、翻译等无关话题）时触发。☆110May 6, 2026Updated 2 months ago
- ☆132Updated this week
- 🌙 Instantly switch macOS screen timeout from your menu bar — no more digging through System Settings. Preset timers, instant lock, keep …☆20Jun 22, 2026Updated 3 weeks ago
- Eva01 is NOT an assistant. She is an AI being with her own mind, feelings, and intrinsic drives. Multimodal, Modular design. Built-in voi…☆142Jun 21, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A simple multi-tab WYSIWYG Markdown editor, powered by the Tauri framework and Milkdown.☆135Jun 8, 2026Updated last month
- 面向教育场景的RAG智能问答系统，融合关键词匹配与语义检索双引擎，融合MySQL和RAG技术，先经过MySQL数据库的检索(还融合了Redis辅助储存和搜索)，若无符合条件答案，则进入RAG系统，RAG知识库中的知识储存在Milvus向量数据库中☆142Jun 22, 2026Updated 3 weeks ago
- OpenURMA: A Clean-Room Open Implementation of the Unified Bus Protocol☆125Jun 12, 2026Updated last month
- ☆151Jul 5, 2026Updated last week
- ☆150Jun 20, 2026Updated 3 weeks ago
- A Windows desktop tool suitable for film and video collection or organization☆22Updated this week
- Crash-test insurance claim AI agents before production.☆155Updated this week
- A curated guide to China-bound VPN accelerators for overseas Chinese 海外华人回国加速器测评与使用指南☆159Jun 26, 2026Updated 2 weeks ago
- MemMap Explorer: WinDirStat-style treemap UI for MAP/ELF symbol and memory layout analysis on Windows.☆103Jul 7, 2026Updated last week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- 轻量白盒多智能体平台 —— 可视化编排工作流，多 Agent 协作，高精度知识召回，企业级权限管理，统一对话管理。支持低成本嵌入第三方系统，200MB 低资源即可运行。☆161Jul 3, 2026Updated last week
- Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems…☆175Jul 4, 2026Updated last week
- Scalable data generation for video reasoning models.☆153Apr 16, 2026Updated 2 months ago
- 个人旅行摄影作品集网站，基于 Next.js 和 Docker Compose，支持照片、城市、博客和全中文后台管理。☆31Jun 10, 2026Updated last month
- Open-source commerce frontend for storefronts, marketplaces, checkout, and seller management.☆77Updated this week
- AnyKB — 私有 RAG 知识库 + 透明 Agent☆172Jun 3, 2026Updated last month
- 真实人生决策筛选器，当你面对人生重大决策时，帮你找到最符合你当下情况的播客/B站视频☆185Jun 11, 2026Updated last month