Voice, Computer-use & Embodied Agents

53 systems · 2,542 edges · 53 visible · data as of 2026-10-31 (991 re-verified that month) · what changed

Voice agent platforms, wearable memory, computer-use agents and robotics stacks.

Click a row to inspect · shift-click rows (2-4) to compare · click headers to sort
System Status Tier Section What it is Modalities Deployment Pricing License Latest release GitHub Verified
Active
T1
Computer-use & desktop agents
Claude desktop-control capability (Anthropic API) ↗ 2
text + screen images ↗ 2
Managed-only — Claude API tool (also Bedrock, Vertex, Foundry); actions execute in a caller-provided desktop environment ↗ 2
Standard Claude API token pricing; ~4.5k input-token toolset overhead plus screenshots billed as image input; no per-action fee ↗ 2
proprietary (Claude API feature) ↗ 2
computer_toolset_20260801 (2026-08) — current tool version, no beta header required ↗ 2
·
2026-10-31
Acquired
T1
Voice-first / wearable AI memory
Audio pendant — never stores raw audio ↗ 2
voice ↗ 2
Managed-only ↗ 2
Bee Frontier bracelet $74.99 (sold via Amazon, launched 2026-10-15); Bee Pro subscription $11.99/mo (free tier keeps 14 days of memory); Bee Eclipse ($100) coming soon ↗ 2
·
·
·
2026-10-29
Active
T1
Voice agent platforms
Developer platform for AI phone agents (vertically integrated) ↗ 2
voice (PSTN) + text ↗ 2
Both (self-hosted + managed cloud) — managed cloud by default; on-prem/VPC deployment on Enterprise only ↗ 2
Start: $0 platform fee + $0.14/connected min; Build: $299/mo + $0.12/min; Enterprise custom ↗ 2
·
·
·
2026-10-26
Active
T1
Computer-use & desktop agents
OSS browser-agent library + Cloud (browser-use) ↗ 2
DOM text + optional screen images ↗ 2
Both (self-hosted + managed cloud) — OSS Python library + Browser Use Cloud; on-prem via sales ↗ 2
OSS library free; Cloud pay-as-you-go: $1 free credit, $5 min top-up, browsers $0.02/hr, agents = model price +20%; on-prem via sales ↗ 2
MIT ↗ ●
v0.13.11 (2026; release date not confirmed) ↗ 2
browser-use/browser-use — ~119k stars, last commit 2026-09+ (release 0.13.10 on 2026-09-04) ↗ ●
2026-10-31
Active
T1
Voice agent platforms
Real-time TTS + voice-agent platform (Cartesia) ↗ 2
voice (TTS + STT) + text ↗ 2
Both (self-hosted + managed cloud) — managed API; on-prem (incl. air-gapped), customer VPC and OEM under enterprise contract ↗ 2
Free (20K credits/mo); Pro $5/mo; Startup $49/mo; Scale $299/mo; Enterprise custom; managed voice agents $0.06/min ↗ 2
·
Sonic-3.6 (current model; release date not stated) ↗ 2
github.com/cartesia-ai (SDKs) ↗ ●
2026-10-26
Active
T1
Computer-use & desktop agents
Consumer browser-agent extension (Chrome) — Anthropic ↗ 2
text + DOM + screen images ↗ 2
Managed-only — Chrome extension in the user's browser; model runs in Anthropic cloud ↗ 2
Not on Free; included in Pro ($20/mo, $17 annual), Max (from $100/mo), Team and Enterprise ↗ 2
·
·
·
2026-10-29
Renamed
T1
Voice agent platforms
Voice-agent platform from a TTS-first vendor (ElevenLabs) ↗ 2
voice (WebRTC + PSTN via Twilio) + text + 30+ languages ↗ 2
Cloud-managed ↗ 2
Per-minute usage (Conv AI tier); free + Pro + Enterprise ↗ 2
·
·
github.com/elevenlabs (SDKs only) ↗ ●
2026-10-29
Active
T1
Robotics foundation models & agent stacks
Humanoid robot maker (Figure 01 / Figure 02 / Helix VLA model) ↗ 2
vision + language + full-body action ↗ 2
Direct customer deployment (humanoid robot) ↗ 2
·
·
Helix 2.5 (2026-09-17) ↗ 2
·
2026-10-29
Active
T1
Voice-first / wearable AI memory
Always-on AI companion pendant ↗ 2
voice ↗ 2
Managed-only ↗ 2
Hardware-bundled ↗ 2
·
·
·
2026-10-28
Active
T1
Robotics foundation models & agent stacks
Robotics foundation model from Google DeepMind ↗ 2
vision + language + action; embodied reasoning ↗ 2
Trusted-tester via partners; Vertex AI / Cloud planned ↗ 2
·
·
Gemini Robotics 2 (with Gemini Robotics ER 2 and On-Device 2; date not stated on the model page) ↗ 2
·
2026-10-29
Active
T1
Voice-first / wearable AI memory
Mac/iOS meeting notepad — system-audio tap ↗ 2
voice ↗ 2
Managed-only ↗ 2
Basic $0; Business $14/user/mo; Enterprise $35/user/mo ↗ 2
·
·
·
2026-10-23
Active
T1
Robotics foundation models & agent stacks
OSS robotics platform on HuggingFace (datasets + models + policies) ↗ 2
vision + language + action; multi-embodiment datasets ↗ 2
Self-hosted only — library (pip install lerobot) ↗ 2
OSS free; HF Hub free + paid tiers ↗ 2
Apache-2.0 ↗ ●
v0.6.1 (2026-08-03) ↗ 2
huggingface/lerobot — ~28.5k stars, last commit 2026-10 ↗ ●
2026-10-27
Shut down
T1
Voice agent platforms
Empathic voice-AI platform (voice + emotion) ↗ 2
voice + text + emotion vectors ↗ 2
Cloud-managed ↗ 2
Per-minute usage; tiered + Enterprise ↗ 2
·
EVI 3 and EVI 4-mini; the EVI API shuts down on 2026-11-13 ↗ 2
HumeAI org (SDKs/examples; hume-api-examples ~250 stars, updated 2026-10) — EVI service closed source ↗ ●
2026-10-29
Acquired
T1
Voice-first / wearable AI memory
Wearable pendant + screen capture lifelog ↗ 2
voice + image ↗ 2
Managed-only ↗ 2
Discontinued — no new sales since 2025-12-05; existing Pendant owners get Unlimited plan free ↗ 2
·
·
·
2026-10-29
Active
T1
Voice agent platforms
Voice-agent framework on LiveKit WebRTC platform ↗ 2
voice + video + text (WebRTC) ↗ 2
Both (self-hosted + managed cloud) — OSS framework self-host + LiveKit Cloud ↗ ●
OSS free; LiveKit Cloud tiered ($50/mo+ + usage) ↗ 2
Apache-2.0 (framework); turn-detector models under LiveKit Model License ↗ ●
v1.7.1 (2026-08-27) — livekit-agents (Python) ↗ ●
livekit/agents — ~13k stars, last commit 2026-08+ ↗ ●
2026-10-26
Active
T1
Robotics foundation models & agent stacks
Robotics foundation model + simulation stack (NVIDIA) ↗ 2
vision + language + action; sim-to-real ↗ 2
On-robot (Jetson Thor) + simulation (Isaac Sim) + training cloud (Cosmos) ↗ 2
OSS weights free; Cosmos / Jetson hardware sold separately ↗ 2
Apache-2.0 code; model weights NVIDIA Open Model License ↗ 2
GR00T N1.7 (2026-04-21) — Isaac-GR00T ↗ ●
NVIDIA/Isaac-GR00T — ~8.3k stars, last commit 2026-10 ↗ ●
2026-10-29
Active
T1
Voice-first / wearable AI memory
Open-source wearable orb + memory graph ↗ 2
voice ↗ 2
Both ↗ ●
Hardware-bundled ↗ 2
MIT ↗ ●
v0.12.522+12522-macos (2026-10-22) ↗ ●
BasedHardware/omi — ~13.2k stars, last commit 2026-10 ↗ ●
2026-10-22
Deprecated
T1
Computer-use & desktop agents
Consumer computer-use agent (browser-only) ↗ 2
text + screen images + keyboard/mouse actions ↗ 2
Cloud (OpenAI-hosted browser sandbox) — no self-host ↗ 2
Bundled with ChatGPT Pro $200/mo ↗ 2
·
·
·
2026-10-31
Active
T1
Voice agent platforms
Speech-to-speech LLM API (OpenAI Realtime) ↗ 2
voice + text (native multimodal) ↗ 2
API (Cloud); no self-host ↗ 2
Audio token-based: $40/$80 per 1M input/output audio tokens (Oct-2024 launch) ↗ 2
·
·
openai/openai-realtime-agents — ~6.9k stars (MIT reference app on Agents SDK), last commit n/a; API itself closed source ↗ ●
2026-10-26
Active
T1
Voice-first / wearable AI memory
Meeting bot + browser extension + app ↗ 2
voice ↗ 2
Managed-only ↗ 2
Basic free; Pro $16.99/user/mo monthly or $8.33 annual; Business $30 list ($19.99 annual); Enterprise custom ↗ 2
·
·
·
2026-10-22
Active
T1
Robotics foundation models & agent stacks
Robotics foundation-model lab (π0 / π0.5) ↗ 2
vision + proprioception + action (continuous) ↗ 2
Both (self-hosted + managed cloud) — openpi weights self-hosted; Pi API beta (managed fine-tuning + hosted inference, waitlist) since 2026-10-13 ↗ 2
·
OpenPI Apache 2.0 (Feb 2025 release of weights) ↗ ●
pi0.7 (2026-04-16) — model; openpi repo has no GitHub releases ↗ 2
Physical-Intelligence/openpi — ~14.4k stars, last commit 2026-08 ↗ ●
2026-10-29
Active
T1
Voice agent platforms
OSS voice-agent framework (Daily.co) ↗ 2
voice + text + video (WebRTC) ↗ 2
Both (self-hosted + managed cloud) — pip self-host + Pipecat Cloud ↗ ●
OSS free; runs on Daily.co Cloud or self-host ↗ ●
BSD-2-Clause ↗ ●
v1.7.0 (2026-08-01) ↗ ●
pipecat-ai/pipecat — ~16.8k stars, last commit 2026-08+ ↗ ●
2026-10-26
Active
T1
Voice-first / wearable AI memory
Magnetic clip-on + AI transcription ↗ 2
voice ↗ 2
Managed-only ↗ 2
NotePin $159 / NotePin S $179 / Note Pro $189; Starter plan free (300 min/mo); Pro $17.99/mo or $99.99/yr (1,200 min); Unlimited $29.99/mo or $239.99/yr ↗ 2
·
·
·
2026-10-22
Archived
T1
Computer-use & desktop agents
Google DeepMind browser-agent (research preview) ↗ 2
text + DOM + screen images ↗ 2
Chrome extension + Google Cloud ↗ 2
Bundled with Gemini Advanced ($19.99/mo) ↗ 2
·
·
·
2026-10-31
Active
T1
Voice-first / wearable AI memory
Meeting bot + analytics + Ada digital twin ↗ 2
voice ↗ 2
Managed-only ↗ 2
Free (5 meetings/mo); Pro $19.75/mo ($15 annual); Enterprise $29.75 ($22.50); Enterprise+ $39.75 ($29.75), per user ↗ 2
·
·
·
2026-10-22
Active
T1
Voice agent platforms
Developer platform for AI voice agents (low-latency) ↗ 2
voice (PSTN + WebRTC) + text ↗ 2
Cloud-managed ↗ 2
Pay-as-you-go $0.07-$0.31/min for voice agents (Retell voice infra $0.055/min plus TTS and LLM components), $10 free credits, 20 concurrent calls included; Enterprise custom ↗ 2
·
·
github.com/RetellAI (SDKs only) ↗ ●
2026-10-27
Active
T1
Computer-use & desktop agents
OSS browser-automation framework (Browserbase OSS) ↗ 2
DOM text + screen images ↗ 2
Both (self-hosted + managed cloud) — library runs locally; Browserbase cloud browsers optional ↗ ●
OSS free; Browserbase Cloud handles runtime ↗ ●
MIT ↗ ●
v3.7.3 (2026-08-28) — @browserbasehq/stagehand ↗ ●
browserbase/stagehand — ~25.5k stars, last commit 2026-08+ ↗ ●
2026-10-26
Active
T1
Robotics foundation models & agent stacks
Robotics research lab — Large Behavior Models (LBM) ↗ 2
vision + proprioception + action ↗ 2
Research-stage; Toyota internal pilots; OSS code for community ↗ 2
·
Some research code OSS (BSD / MIT) ↗ ●
LBM paper, A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation (2025-07-07) ↗ 2
ToyotaResearchInstitute (org) — 123 public repos incl. lbm_eval (~125 stars), last activity 2026-10 ↗ ●
2026-10-29
Active
T1
Voice agent platforms
Developer platform for AI voice agents (programmable telephony) ↗ 2
voice (PSTN + WebRTC) + text ↗ 2
Cloud-managed; private deployments on Enterprise tier ↗ 2
Per-minute usage ($0.05/min base + provider passthrough) ↗ 2
·
·
github.com/VapiAI (SDKs only) ↗ ●
2026-10-26
Active
T2
Robotics foundation models & agent stacks
Humanoid robot maker (Neo / Eve) — OpenAI portfolio ↗ 2
vision + language + bimanual action ↗ 2
Direct customer (industrial Eve + consumer Neo) ↗ 2
NEO: $20,000 early-access purchase (3-yr warranty) or $499/month subscription; $200 refundable deposit ↗ 2
·
NEO home humanoid (orders opened 2025-10-28; US deliveries slated 2026); NEO hands platform (2026-07-09) ↗ 2
·
2026-10-26
Active
T2
Robotics foundation models & agent stacks
Bipedal warehouse robot maker (Digit) — first US humanoid commercial deployment ↗ 2
vision + language + bipedal action ↗ 2
Warehouse deployment; RaaS model ↗ 2
Robot-as-a-Service (RaaS) — vendor reports per-hour rates ↗ 2
·
Digit 5 (unveiled 2026-09-15; early access H1 2027, GA by end-2027) ↗ 2
·
2026-10-26
Active
T2
Robotics foundation models & agent stacks
Humanoid robot maker (Apollo) — Google DeepMind partner ↗ 2
vision + language + bimanual action ↗ 2
Direct customer (manufacturing + logistics) ↗ 2
·
·
Apollo (humanoid) ↗ 2
·
2026-10-27