psyb0t
12 repositories in the Claude AI ecosystem, indexed and ranked by ClaudeWave.
Stealth browser automation that actually works. Runs Camoufox (custom Firefox) in Docker with zero Chrome DevTools Protocol exposure, real OS-level mouse and keyboard input via PyAutoGUI, and a JSON HTTP API + MCP server to control it all remotely. Watch it live via noVNC.
Claude Code in Docker. Drop-in OpenAI-compatible API, MCP server, Telegram bot, and CLI — five interfaces, one image. Persistent sessions, file ops, always-on skill injection, and a full dev toolchain (Go, Python, Node, K8s, Terraform, databases) or a minimal image with just the basics.
OpenAI-compatible audio server in Docker. 7 ASR backends (Whisper, Distil-Whisper, Parakeet, Canary, Canary-Qwen) + 2 TTS engines (Kokoro, Qwen3-TTS voice cloning). Single /v1/audio/{transcriptions,speech,voices} surface. CPU + CUDA images. Hot model swap. MCP server built in.
Lightweight object storage that speaks S3 (boto3/AWS SDK compatible), plain HTTP, and MCP. SQLite for metadata, flat files on disk.
Self-hosted forecasting + prediction service. Five zero-shot time-series foundation models (Chronos-2, TimesFM 2.5, Moirai-2, Toto-1, Sundial) across six forecast types, plus nine supervised tabular ML backends (LightGBM, XGBoost, sklearn family) with calibrated / stacking / diversified meta-learners. Unified REST API + MCP server.
Self-hosted video API in one Docker container. Lipsync (LatentSync 1.5, Wav2Lip), face restoration (GFPGAN), ffmpeg ops (trim/concat/transcode/scale/mux/extract/thumbnail/gif), ffprobe metadata, async jobs + webhooks. REST + MCP. CPU + CUDA. Drive from shell, generated Go/Python clients, or LLM agent.
Dumb-as-rocks OHLC analyzer. POST your bars + the indicators you want, get back exactly what you asked for. RSI/MACD/Bollinger/ADX/ATR/VWAP/Ichimoku, plus SMC primitives: Order Blocks, FVGs, BOS/CHoCH, swing structure. Stateless HTTP + MCP, no database, no AI-powered signals, no $97/mo Discord upsell.
OpenAI Codex CLI inside an aicodebox container. One image, five ways in: interactive shell, one-shot exec, OpenAI-compatible endpoint, MCP server, Telegram bot, and a cron scheduler. You talk to codexbox; codexbox talks to codex; codex talks to OpenAI — or your ChatGPT subscription.
Self-hosted audio API in one Docker container. Stem separation, mastering, MIR (BPM/key/chords), audio→MIDI, text-to-music + SFX (MusicGen/Stable Audio/Riffusion/AudioLDM2), diarization, speech enhancement, restoration, embeddings + zero-shot tagging, workflows, async + webhooks. REST + MCP. CPU + CUDA.
pi-coding-agent inside an aicodebox container. One image, five ways in: interactive shell, one-shot API, OpenAI-compatible endpoint, MCP server, Telegram bot, and a cron scheduler that fires pi on whatever schedule you want. You talk to pibox. pibox talks to pi. pi talks to whatever LLM you point it at. Nobody cares about the middle.
Multi-mailbox IMAP/SMTP control plane. One YAML, N accounts, one bearer-auth gate. Unified inbox across Gmail/Outlook/iCloud/mailo/inbox.lv/whatever — search, read, mark, send. Reader mode strips HTML chrome for LLMs. Streamable-HTTP MCP server + REST API on one port. Ships as a Docker image.
Your Telegram account, but it takes HTTP requests. Wraps Telethon — the real MTProto userbot client, not that neutered Bot API garbage — behind a JSON HTTP API and a Model Context Protocol endpoint.