UI-TARS-desktop
AI agentsByteDance's multimodal AI agent stack for desktop automation.
2,992 results · Page 80 of 84
ByteDance's multimodal AI agent stack for desktop automation.
Open-source AI design Skill, designed specifically for AI coding assistants
Trust scores and guardrails for AI-generated code: static security rules, Docker-verified build/boot checks and receipts that catch agents lying about tests.
AI-powered codebase and knowledge base analysis tool that builds interactive visual knowledge graphs. Features multi-agent analysis, architecture guided tours, and semantic search for large codebases. Works as a plugin for Claude Code, Cursor, and more.
Local-first desktop agent that can control GUI apps, browser, shell, and messaging channels, and can learn repeatable tasks from a single demonstrated run.
TCG collectibles and agent utilities: AI card grading, Monte Carlo price simulation, music and image generation, TTS, RAG memory and SAST auditing.
Resolve an agent's intent to the right MCP server across registries, with an invocation-ready snippet and an Ed25519-signed trust passport.
MCP aggregator that connects agents to multiple MCP servers through one configuration, with ready-made templates and cross-repo prompt workflows.
The introduction is being prepared. Please check back soon.
Edge computing devices and boards for industrial automation and AI solutions.
AI agents to enhance business workflows and boost productivity.
Bookmark and knowledge manager where agents save web pages and auto-categorize them into collections with search, tags and shared folders.
Turn a Mac into a remote computer-use server via CUA: screenshots, mouse, keyboard, windows and apps, token-protected and exposed through a Cloudflare tunnel.
#️⃣ 🏠 - Simulated smart home and lifestyle devices for testing an agent's reasoning and discovery capabilities.
No-code platform to build and deploy AI chatbots and agents with custom ChatGPT.
AI workflow automation platform that uses autonomous coworkers to execute tasks across connected apps.
Share end-to-end encrypted, self-destructing secrets from an agent, reading them from env vars or files so they stay out of LLM context.
AI-Powered Automation Purpose-Built for P&C Insurance Operations
Vectara is an enterprise-grade agent platform for building governed, grounded, auditable AI agents, supporting global enterprise applications across industries. It can transform complex multimodal data into actionable intelligence, unify data and deliver context, making every answer traceable. The platform covers data ingestion and parsing, hybrid retrieval and reranking, hallucination detection and evaluation, as well as agent orchestration (skills, tools, MCP, memory, sub-agent workflows). It can be integrated into applications via REST API, MCP, and A2A. It supports SaaS, VPC, and on-premises deployment, and allows bringing your own LLM or using its models. In scenarios such as semiconductors, it already has uses in design, fabs, assembly and test, packaging, and quality, and has published customer cases including improving retrieval accuracy from 40% to 90%, reducing failure analysis time by 30%, and going from POC to production in 3 months.
VectorTrees enhances sales productivity using AI-driven automation to solve key sales challenges.
Stealth automation of unmodified Chrome over raw CDP, using accessibility-tree element refs; can attach to a running Chrome to reuse logged-in sessions.
AI-powered customer success platform for proactive customer management and automation.
Vengo AI: AI platform for creating and monetizing digital twins and AI sales agents.
VenueLog simplifies venue management with integrated systems, automation, and AI-powered insights.
Multi-AI crypto token risk scanner for Solana, Base and Ethereum: agents debate risk to detect rug pulls, honeypots, holder concentration and wash trading.
Fail-closed trust gate for agents: fact-checking, prompt-injection detection, content moderation, PII and secret detection, and a pre-action guardrail.
Official connector CLI with JSON-first agent-friendly connector invocation, managed connectors, and bundled skill docs for open-source workflows.
Specialist agent council for AI coding CLIs with a self-learning router, cross-CLI memory and guards against dependency hallucinations and decision drift.
AI-powered documentation automation for veterinary clinics.
Self-hosted stealth Chrome automation via Patchright: parallel persistent profiles, encrypted credential vault with 2FA, and prompt-injection scanning.
Prevent cascading errors and scope creep by calling a vibe-check agent to ensure user alignment.
Local safety layer for coding agents: deterministic risk checks, checkpoints and policy inspection, plus restoring files to their pre-session state.
Code-aware browser testing that reads routes, forms and existing tests, runs Playwright scenarios, and keeps regression history and screenshot reports.
The introduction is being prepared. Please check back soon.
Unified CLI for running Claude Code, Codex, OpenCode, Pi, and other AI coding agents in isolated Docker or Podman containers, with local metrics and an analytics dashboard.
The introduction is being prepared. Please check back soon.