Catalog Catalogs Voice, Computer-use & Embodied Agents

Voice, Computer-use & Embodied Agents

Voice agent platforms, wearable memory, computer-use agents and robotics stacks. For builders of agents that speak, see a screen or act in the world.

Voice agent platforms, voice-first and wearable memory products, computer-use and desktop agents and robotics foundation models, with modalities, deployment, pricing and lifecycle.

52 systems · 4 sections · 11 acquired, archived, stale or shut down · data as of 2026-10-31

Browse the table → JSON · CSV

Decide

Most referenced

Lowest tier first, then by how many other systems in the catalog reference each one.

  1. Cartesia Sonic T1 Real-time TTS + voice-agent platform (Cartesia)
  2. LiveKit Agents T1 Voice-agent framework on LiveKit WebRTC platform
  3. ElevenLabs Conversational AI (now ElevenAgents) T1 Renamed Voice-agent platform from a TTS-first vendor (ElevenLabs)
  4. OpenAI Realtime API T1 Speech-to-speech LLM API (OpenAI Realtime)
  5. Pipecat (Daily) T1 OSS voice-agent framework (Daily.co)
  6. Browser Use T1 OSS browser-agent library + Cloud (browser-use)
  7. Stagehand T1 OSS browser-automation framework (Browserbase OSS)
  8. Hume EVI T1 Shut down Empathic voice-AI platform (voice + emotion)
  9. Bland AI T1 Developer platform for AI phone agents (vertically integrated)
  10. Vapi T1 Developer platform for AI voice agents (programmable telephony)
  11. Google DeepMind Gemini Robotics T1 Robotics foundation model from Google DeepMind
  12. Granola T1 Mac/iOS meeting notepad — system-audio tap

All 52 in the table →

Sections

Lifecycle

  • Active 40
  • Renamed 1
  • Acquired 3
  • Stale 1
  • Deprecated 3
  • Archived 3
  • Shut down 1

Tiers: T1 28 · T2 16 · T3 7 · T4 0 · T5 1

Recently changed

  • UI-TARS Latest release: UI-TARS-desktop / Agent TARS v0.3.1 (2026-10-09); UI-TARS-2 announced 2025-09-04; latest open weights UI-TARS-1.5-7B (2025-04-16)
  • Claude for Chrome Homepage: https://claude.com/resources/articles/claude-for-chrome
  • ElevenLabs Conversational AI (now ElevenAgents) Name: ElevenLabs Conversational AI (now ElevenAgents)
  • Era Computer Homepage: https://era.world/
  • Google DeepMind Gemini Robotics Homepage: https://deepmind.google/models/gemini-robotics/ · Latest release: Gemini Robotics 2 (with Gemini Robotics ER 2 and On-Device 2; date not stated on the model page)
  • Hume EVI Homepage: https://dev.hume.ai/voice/docs/speech-to-speech-evi/overview
  • Magnitude Homepage: https://magnitude.dev/
  • NVIDIA GR00T / Isaac Homepage: https://www.nvidia.com/en-us/industries/robotics/isaac-groot/

Everything that changed →

Research

Data and tools

  • JSON · CSV, flattened, one row per system, CC-BY-4.0
  • MCP tools: plan_stack, ask_catalog, find_alternatives
  • CLI: landscape stack --product voice-agent · landscape search
  • Data & API · Submit a system