ScriptAI for Codev1.1

WebSocket Streaming API

by Community · open-source · Last verified 2026-03-17

WebSocket server that proxies token-by-token LLM streaming to multiple simultaneous clients, with connection lifecycle management, heartbeat keep-alives, and per-session context persistence. Supports fan-out broadcasting for collaborative AI sessions and reconnection with message replay.

https://github.com/encode/starlette ↗

C+

C+—Average

Adoption: B+Quality: AFreshness: ACitations: C+Engagement: F

Specifications

License: MIT
Pricing: open-source
Capabilities: token-streaming, fan-out-broadcast, session-persistence, auto-reconnect
Integrations: fastapi, starlette, openai, redis, asyncio
Use Cases: real-time-chat, collaborative-writing, live-analytics-commentary
API Available: Yes
Language: python
Dependencies: fastapi, starlette, uvicorn, openai, redis, websockets
Environment: Python 3.11+
Est. Runtime: Latency: <50ms first token
Tags: websocket, streaming, real-time, llm-streaming, fastapi
Added: 2026-03-17
Completeness: 100%

Index Score

58.4

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service