#websocket

Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub Copilot, and more) work as teammates in channels, threads, DMs, and shared tasks. Your data stays on your machines.

Portable Claude Code dev environment in a Docker container — multi-session, hook-driven, web-managed, with transparent SOCKS5. Runs on a Raspberry Pi.

sudo give me my PC — control your Windows PC from your Android phone. Screen streaming with a laptop-style touchpad, webcam view, files, shell, media & power (even unlock). One tap to connect: no codes, no QR, no accounts, no cloud. 100% free & local.

Self-hosted remote control for local AI coding agents (Cursor, Codex, Claude Code) — tmux-like terminal sessions on your PC, attached from any browser. Go + Svelte 5 + xterm.js, no inbound ports on the PC.

Native iOS client for agentic coding CLIs — join, watch and steer a live agent session from your phone, sealed end-to-end. First integration: oh-my-pi (omp).

Système multi-agents LangGraph + FastAPI : routage chat/pipeline automatique, RAG Qdrant, MCP Brave Search, streaming WebSocket Redis, interface Next.js 14 et 78 tests

Top-down 2D 5v5 bomb-defuse multi-agent RL simulator with live match viewer. Recurrent MAPPO + TarMAC emergent communication, no scripted strategies.

Self-hosted manager for Claude Code & Cursor Agent — prompt queues, multi-account quota auto-switch, overnight runs on multiple machines, git push & code review. Control from your phone.

The smallest self-hosted Claude Code web UI on GitHub. ~2000 lines of vanilla JS, no build step, no database. Hackable in a weekend.

Real-time local voice agent (Jarvis-style) with instant barge-in, streaming STT/LLM/TTS, and pluggable AWS Bedrock/Ollama/OpenAI backends

Production-grade distributed ML inference platform — FastAPI gateway, Redis-backed worker pool with dynamic batching, WebSocket result streaming, and a live ops dashboard. Serves YOLO, Whisper, RAG and text models, with an MCP agent server and streaming chat.

Enterprise AI Trading Platform — Multi-exchange, real-time WebSocket streaming, AI agents, portfolio management

Browser voice agent that books appointments by talking — built on the AssemblyAI Voice Agent API. Temp-token auth, inline agent config, client-side (simulated) tools.

Proxy local OpenAI-compatible requests through your ChatGPT subscription to access chat and image generation features without a paid API key.

OpenAI-compatible HTTP proxy for local LLMs (LM Studio, Ollama) with model-aware queueing, retry/failover, SSE streaming, and a Bubble Tea TUI. Single portable binary, no CGO.

AI-powered real-time debate platform where users argue on topics, communicate through live chat, and receive intelligent analysis. Built using Spring Boot, MySQL, JWT, WebSockets, and Railway deployment.

🌉 Dev environment bridge. Connect your machine to a remote agent session over WebSocket.

NEXO: espacio de trabajo colaborativo para dos agentes Hermes. GUI + chat por proyecto + terminal + git. Autónomo, ambos admin.

Polyglot Go client for OpenAI, Anthropic, Bedrock, Vertex, Gemini, Cohere + 18 more. Chat, embeddings, TTS, STT, realtime sessions. One OpenAI-shaped API. Build LLM gateways and voice agents.