# Show HN: StreamCore – Open-source realtime voice infrastructure for AI > Source: > Published: 2026-08-28 14:38:05+00:00 **Talk to your AI over WebRTC — with interruption, streaming speech, and NAT traversal handled.** One Go binary. Bring your own agent. No install, no signup — browser mic, and you can cut it off mid-sentence. [ Live demo](https://streamcore.ai) · [·](#quick-start) **Quick start**[·](/streamcoreai/streamcore-server/blob/main/docs) **Docs**[·](#sdks-and-examples) **SDKs**[·](/streamcoreai/streamcore-server/blob/main/docs/roadmap.md) **Roadmap**[·](https://discord.gg/xKGFaGWawT) **Discord**[简体中文](/streamcoreai/streamcore-server/blob/main/README.zh-CN.md) Anyone can demo a voice agent. Then a real caller talks over it, pauses mid-sentence, dials in from behind a firewall that blocks UDP, or waits three seconds for the first word — and the demo stops being a product. StreamCore is the layer that handles all of that. It owns the latency-sensitive media path between your users and your AI: **WebRTC transport, adaptive turn-taking, barge-in, streaming STT/LLM/TTS, NAT traversal, session state, and realtime events** — across browsers, phones, backends, telephony, and embedded devices. What it deliberately does *not* own is your agent. Keep your prompts, tools, models, and business logic exactly where they are — [four supported ways](#bring-your-own-agent), no fork required. Built with it: voice agents, realtime copilots, live translation, AI-hosted audio rooms, embedded voice devices, and phone applications. ** streamcore.ai runs this repo.** Open it, hit *Start Conversation*, and interrupt the agent while it is talking. Per-turn STT, LLM, and TTS latency is on screen while you do it. Prefer a recording? [Watch the walkthrough](https://www.loom.com/share/ee079aca75aa4fa1ba6a5e51302fbd56). **Two terminals, five minutes, and you are talking to it.** Needs Go 1.25+ (or Docker) and API keys for an STT, LLM, and TTS provider. No keys? Run it [fully local](/streamcoreai/streamcore-server/blob/main/docs/quickstart.md#fully-local-no-api-keys) with Ollama + VibeVoice. ``` cp config.toml.example config.toml # add your provider credentials go run . ``` The server listens on `:8080` ; clients connect to `http://localhost:8080/whip` . Then talk to it from a browser: ``` git clone https://github.com/streamcoreai/examples.git cd examples/typescript && npm install && npm run dev ``` Open [http://localhost:3000](http://localhost:3000) and start talking. Docker, TURN ports, and production notes: [Quick start guide](/streamcoreai/streamcore-server/blob/main/docs/quickstart.md). Transport | WebRTC audio over WHIP ( | **Connectivity*** and*TCP 3478 — no external coturn. A network handover or NAT rebind is recovered by ICE restart on the same session, so the conversation survives it**Turn-taking****Interruption****Streaming****Sessions & events****Reach**[SIP telephony](https://github.com/streamcoreai/sip-server), and[ESP32](https://github.com/streamcoreai/esp32)endpointsFull capability list: [Capabilities](/streamcoreai/streamcore-server/blob/main/docs/capabilities.md). Listed so the table above stays honest — unticked items are real gaps today, not soon-shipping promises. Ticked ones shipped recently and stay listed for a release or two so you can see what moved: - **Session reconnection (server)**— a dropped connection recovers on the same session via ICE restart, so the conversation and the running pipeline survive it - **Client-driven reconnection**— the TypeScript, React Native, Go and Rust SDKs recover a network change automatically: ICE restart first, then a resume redial if the connection failed - **Session resume**— a drop past the point ICE restart can help is recovered by redialling with a single-use token, reattaching to the running conversation. Every SDK runs restart-then-resume as one ladder, so a backgrounded phone rejoins the same conversation - **Panic recovery**— a panic in one call's goroutines now ends that call alone: it recovers, logs the stack, and the session is reaped like any other ended call - **Session cap**—`server.max_sessions` bounds live sessions globally; past it,`POST /whip` returns 503 with`Retry-After` . Resumes are exempt - **Env-var secrets**— every API key and secret can come from the environment (`OPENAI_API_KEY` ,`STREAMCORE_JWT_SECRET` , …) instead of`config.toml` . See[Configuration](/streamcoreai/streamcore-server/blob/main/docs/configuration.md#secrets-from-environment-variables) - **Metrics export**—`/health` and timing events exist, no Prometheus/OpenTelemetry - **Structured logging**—`log.Printf` text today, no JSON logs carrying`session_id` - **Versioned releases**— a Docker image ships to GHCR on each GitHub release, but no version in the binary and no tagged standalone binaries yet - **Horizontal scaling**— sessions live in process memory, so the server is single-node; reconnection and resume need sticky routing or an external store to work behind a load balancer - **HTTP agent endpoint**—`llm.provider = "agent"` POSTs each turn to an agent you host in any language; replies stream back as speech - **Persistent memory**— the built-in runtime forgets callers between sessions; BYO agents can already persist their own Full TODO list, including ecosystem items: [Roadmap / TODO](/streamcoreai/streamcore-server/blob/main/docs/roadmap.md). Want one of these? Say so in [Discord](https://discord.gg/xKGFaGWawT) — demand reorders the list. StreamCore starts one layer below prompt-and-tool frameworks: the media path. Your intelligence stays yours, five ways — **Tool call**— plugins (Python/TS/JS) or native Go tools call into your existing backend** Your agent**— set`llm.provider = "agent"` and each turn is POSTed to an HTTP endpoint you host, in any language**Your models**— point`llm.provider = "ollama"` at any Ollama-compatible URL you run**Your code**— implement one small Go interface; the whole media path works unchanged** Built in**— or use StreamCore's optional agent runtime with tools, skills, RAG, and history Details and code: [Bring your own agent](/streamcoreai/streamcore-server/blob/main/docs/bring-your-own-agent.md) · [Agent runtime](/streamcoreai/streamcore-server/blob/main/docs/agent-runtime.md). Providers: Deepgram, AssemblyAI, OpenAI, Cartesia, ElevenLabs, MiniMax, Speechify, Ollama, VibeVoice (local), xAI Grok Voice (speech-to-speech), pgvector/Supabase for retrieval. See [Providers](/streamcoreai/streamcore-server/blob/main/docs/providers.md). | Page | What's in it | |---|---| | [Capabilities](/streamcoreai/streamcore-server/blob/main/docs/capabilities.md)[Bring your own agent](/streamcoreai/streamcore-server/blob/main/docs/bring-your-own-agent.md)`llm.Client` interface[Agent runtime](/streamcoreai/streamcore-server/blob/main/docs/agent-runtime.md)[Providers](/streamcoreai/streamcore-server/blob/main/docs/providers.md)[Configuration](/streamcoreai/streamcore-server/blob/main/docs/configuration.md)`config.toml` reference[Protocol](/streamcoreai/streamcore-server/blob/main/docs/protocol.md)[Architecture](/streamcoreai/streamcore-server/blob/main/docs/architecture.md)Connect from anywhere — every SDK speaks the same WHIP + DataChannel protocol: React Native / Expo (`@streamcore/react-native-sdk` ) is built but not yet published to npm. Plugin SDKs: `@streamcore/plugin` and `streamcore-plugin` in [plugin-sdk](https://github.com/streamcoreai/plugin-sdk). Runnable browser, CLI, and TUI apps: [examples](https://github.com/streamcoreai/examples). Thank you! Interested in sponsoring? Reach out for logo placement on GitHub + demo page. Read [CONTRIBUTING.md](/streamcoreai/streamcore-server/blob/main/CONTRIBUTING.md) first — it covers running the server locally, the four checks CI runs before you push, and the extra care the timing-sensitive media path needs. Good places to start: [ good first issue](https://github.com/streamcoreai/streamcore-server/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) and [.](https://github.com/streamcoreai/streamcore-server/issues?q=is%3Aissue+is%3Aopen+label%3A%22help+wanted%22) `help wanted` Client SDKs, the SIP bridge, examples, and the ESP32 firmware live in their own repos under [ streamcoreai](https://github.com/streamcoreai) — send those changes there. Found a vulnerability? Don't open a public issue — report it privately through the [Security tab](https://github.com/streamcoreai/streamcore-server/security/advisories/new). [SECURITY.md](/streamcoreai/streamcore-server/blob/main/SECURITY.md) covers scope, response targets, and the settings that matter on a public address — JWT auth on `/whip` above all. Apache 2.0. See [LICENSE](/streamcoreai/streamcore-server/blob/main/LICENSE).