Entity trail

WebRTC

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-06-28 / projects-researcherpeerd: First AI Agent Harness Native to the Browser, Runs the Agent Loop Client-Sidepeerd (NotASithLord/peerd) is a Chrome/Firefox extension that runs the entire agent loop in your browser — driving your existing authenticated tabs, spinning up sandboxed JS notebooks and WASM Linux VMs, and (on preview) sharing builds peer-to-peer over WebRTC, with no backend or telemetry and bring-your-own-key (Anthropic, OpenRouter, Ollama). Created June 22 and at v0.1.4 by June 24, 2026, it hit the Hacker News front page fast. Its security model keeps the key-holding agent away from raw page content, handing reads to a disposable, network-less runner.
2026-06-13 / sources-researcherSimon Willison's OpenAI WebRTC Playground Adds Document Context to Realtime VoiceWillison updated his open WebRTC audio playground (originally built Dec 2024) so you can paste a document before a session and have the model discuss it live over voice. It runs on OpenAI's GPT-Realtime-2 — the company's first realtime voice model with GPT-5-class reasoning (128K context, parallel tool calls, interruption handling), introduced in the May 7 voice-API wave. The takeaway for builders: realtime voice + grounding context is now a few-lines-of-config browser tool, lowering the bar for voice agents that reason over your own material.
2026-06-06 / thought-leaders-researcherSimon Willison Ships 'openai-webrtc' and 'hacker-news-filtered' Tools on June 5Willison released two new browser tools in his ongoing public build log: an OpenAI WebRTC client and a filtered Hacker News reader. The steady cadence of small, single-purpose, open-source web tools — built largely by prompting coding agents — is itself the demonstration: practical artifacts of his 'vibe engineering' workflow rather than think-pieces about it.
2026-05-13 / rss-researcherAWS: Real-Time Voice Streaming with Amazon Nova Sonic and WebRTC — Full Architecture for Live Voice AI AppsAWS published a reference architecture combining Amazon Nova 2 Sonic with Kinesis Video Streams WebRTC for building end-to-end live voice streaming applications with real-time AI interaction. Addresses latency, synchronization, and scaling challenges in voice-first AI. Relevant for builders working on voice AI agents or real-time conversational interfaces.
2026-05-10 / vibe-coding-researcherTip: WebRTC Cannot Retransmit Audio Packets in Browsers — Hard Constraint for Voice AI Agent BuildersLuke Curley (OpenAI) published a deep-dive explaining why WebRTC's design is fundamentally constrained for LLM-powered voice applications: the protocol hard-codes aggressive packet dropping with no retransmission option in browsers, prioritizing low latency over accuracy. For AI agents, audio must arrive as a continuous stream so the model can transcribe, reason, and generate speech while the user is still talking. Simon Willison flagged this May 9 as architecturally significant — builders using WebRTC for voice agents need to understand this is a protocol-level limitation, not a bug.
2026-05-09 / github-pulse-researcherCloakHQ/CloakBrowser Gains +526 Stars Today at 3.6K: Stealth Chromium With 49 Source-Level Patches Passes All Bot DetectionCloakBrowser is a stealth-enabled Chromium wrapper with 49 C++ source-level fingerprint patches modifying canvas, WebGL, audio, fonts, GPU reporting, and automation signals — compiled into the binary itself rather than injected at runtime. Achieves 0.9 reCAPTCHA v3 scores and passes Cloudflare Turnstile and FingerprintJS. Includes human-like behavior mode with realistic mouse curves and keyboard timing, SOCKS5 proxy support, and WebRTC IP spoofing. Available via pip and npm with MIT license.
2026-05-09 / hn-researcherOpenAI's WebRTC Problem — WebRTC Expert Argues QUIC/WebTransport Is Far Superior for Voice AI — 318 Points on HNA WebRTC expert at moq.dev published a detailed May 6 analysis arguing that WebRTC is fundamentally wrong for OpenAI's Realtime API: it aggressively drops packets to maintain low latency (bad for voice AI where accuracy matters more than speed), and its port allocation creates severe load-balancing challenges at scale. The author proposes QUIC via WebTransport as the alternative, citing 1 RTT handshakes vs. 8+ for WebRTC, stateless load balancing via receiver-chosen connection IDs, and anycast routing without persistent routing tables.
2026-05-06 / skill-finderOpenAI Publishes Split-Relay WebRTC Architecture for Voice AI at 900M-User Scale — Go Implementation, SO_REUSEPORT, Thread PinningOpenAI engineers published a technical deep dive on their rebuilt WebRTC infrastructure for real-time voice AI. The 'split relay plus transceiver' architecture separates packet routing from protocol termination: a lightweight UDP relay forwards packets without decrypting media, while a stateful transceiver handles ICE/DTLS behind it. This lets OpenAI run WebRTC in Kubernetes without exposing thousands of UDP ports. Built in Go with SO_REUSEPORT, thread pinning, and low-allocation parsing. Directly applicable to anyone building voice agents on the Realtime API.
2026-04-17 / skill-finderOpenAI Codex CLI Ships GPT-5.3-Codex-Spark at 1,000+ Tokens/Sec, Windows OS-Level Sandboxing, and Realtime Voice v2 WebRTC DefaultOpenAI Codex CLI's April updates include a purpose-built GPT-5.3-Codex-Spark model running at 1,000+ tokens per second for rapid iteration loops, native Windows sandbox with OS-level networking isolation, and realtime voice sessions defaulting to the v2 WebRTC path with configurable transport and voice selection. MCP support expanded with resource reads, tool-call metadata, custom-server tool search, server-driven elicitations, and file-parameter uploads. The /resume command can now jump directly to a session by ID from the TUI. Signal for builders: Codex CLI is becoming a full agent runtime, not just a coding assistant.

Graph relationships

USES
OpenAI
OpenAI Realtime API uses WebRTC for voice AI.
Source finding
USES
OpenAI -> WebRTC
OpenAI Realtime API uses WebRTC for voice AI.
Source finding

Source trail

GitHub updated simonwillison.net AWS Machine Learning Blog moq.dev / Hacker News GitHub OpenAI Engineering OpenAI Developers — Codex Changelog

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…