psyb0t

pi-coding-agent (earendil-works) running on the network inside an aicodebox container. Exposes seven programmatic surfaces on one image — interactive shell, one-shot exec (`-p "..."`), an HTTP REST API (run/async/cancel, workspace file ops), an OpenAI-compatible `/openai/v1/chat/completions` endpoint (streaming, client-executed tool calling, response_format/JSON-schema), an MCP server at `/mcp` (mounted in API mode or as a sidecar), a Telegram bot, and a cron scheduler that fires pi on a schedule. Foreground modes (API/Telegram/Cron) are mutually exclusive except Telegram+Cron; MCP coexists with any of them. Bearer-token auth per surface (`PIBOX_API_MODE_TOKEN`, `PIBOX_MCP_MODE_TOKEN`), empty = no auth. Use when the user wants to drive pi-coding-agent programmatically over HTTP/MCP/Telegram/cron instead of a local terminal session, or needs to reason about which pibox mode/endpoint fits a given integration.

Self-hosted AI platform — one `docker-compose up`, one OpenAI-compatible endpoint at http://localhost:4000. Bundles inference (Groq/Cerebras/OpenRouter/HuggingFace/Mistral/Cohere/Ollama/vLLM/llama.cpp/claudebox/pibox-zai/Anthropic/OpenAI), MCP tool use, a stealth browser cluster, image generation (FLUX/DALL-E/SD), speech synthesis (Kokoro/Qwen3-TTS/OpenAI TTS), transcription (Whisper/Parakeet), S3-compatible object storage, agentic code execution (Claude Code + pi-coding-agent + sandboxed piston), web search (SearXNG), an email gateway (mailbox), a Telegram client (Telethon), time-series forecasting + tabular ML (predictalot), audio/video production (audiolla/flickies), an async job queue (proxq), and a web UI (LibreChat) — all reachable through one bearer token and automatic per-model fallback routing. Use when the user wants a one-command self-hosted OpenAI-compatible stack that aggregates many providers/tools behind a single endpoint instead of wiring each service up individually.

Multi-mailbox IMAP/SMTP control plane exposed as a REST API + MCP server (streamable HTTP) on a single port. Read, search, send, mark-seen, and delete mail across multiple inboxes in one call — `GET /inbox` fans out across every IMAP account in parallel and returns a merged, newest-first feed. Use when you need an agent (or a script, or a curl one-liner) to drive one or more real mail accounts without standing up a webmail UI, a message store, or any per-provider client library. Stdlib `imaplib`/`smtplib` under the hood, FastAPI on top, bearer-token auth optional.

Connect to a user-deployed audiolla server to perform stem separation, mastering, MIR analysis, DSP transforms, and loudness normalization on audio files.

Self-hosted OpenAI-compatible speech service. /v1/audio/transcriptions fronts 12 open ASR models (Whisper, Parakeet, Nemotron-3.5-ASR, Canary, Sherpa-ONNX, Vosk); /v1/audio/transcriptions/stream accepts live PCM over WebSocket. /v1/audio/speech fronts 2 TTS engines / 3 backends — Kokoro-82M (41 baked voices, PyTorch + ONNX runtimes) and the CUDA-only Qwen3-TTS family (voice cloning, preset speakers, voice design). Stereo diarization, URL fetching, MCP endpoint, bearer auth.

Text-to-speech generation via Qwen3-TTS over SSH. Preset voices, voice cloning, voice design. Use when the user wants to generate speech audio, clone voices, or work with TTS.

HTTP client for a user-deployed mt5-httpapi MetaTrader 5 bridge. Use ONLY when the user has explicitly installed and configured mt5-httpapi AND provided MT5_API_URL. Read endpoints (account, symbols, rates, ticks, server-side technical-analysis enrichment via the wickworks sidecar, history, backtest report fetching) are safe to invoke. Trade-mutating endpoints on /orders and /positions require explicit per-action confirmation showing symbol, side, volume, and SL/TP; terminal shutdown/restart also require explicit confirmation naming the target terminal and operation. Never invoke mutations on inferred intent. Do not use this skill for generic market-data, charting, or trading questions where the user hasn't named mt5-httpapi.

Headless-detection-resistant browser automation in Docker for authorized QA, compatibility testing, and defensive security research. Camoufox + OS-level input + persistent fingerprints. Use only with sites you own or have written authorization to test.

OpenAI Codex CLI running inside an aicodebox container, put on the network. Exposes seven ways in — interactive shell, one-shot exec, an HTTP REST API (workspace file ops, sync/async prompt runs with run-id polling), an OpenAI-compatible /openai/v1/chat/completions endpoint (streaming, client-executed tools/tool_choice, response_format/JSON-schema), an MCP server (streamable HTTP, mounted at /mcp in API mode or as a sidecar), a Telegram bot, and a cron scheduler that fires codex on a schedule. Auth is bearer-token per surface (CODEXBOX_API_MODE_TOKEN, CODEXBOX_MCP_MODE_TOKEN) plus codex's own OpenAI API-key or ChatGPT-subscription login. Use when the user wants to run OpenAI Codex programmatically over HTTP/MCP/Telegram/cron instead of only in a local terminal, or wants an OpenAI-compatible endpoint backed by Codex.