Projects with this topic
-
Self-hosted stack to index Anna's Archive book metadata and download books via BitTorrent — search API, download API, and PostgreSQL, ready to run out of the box.
Updated -
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.
Updated -
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.
Updated -
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.
Updated -
Agent-agnostic base image for putting any terminal AI coding agent (claude-code, pi, opencode...) on the network. Bolt on a 20-line adapter, get an HTTP API, OpenAI-compatible /v1/chat/completions, MCP server, Telegram bot, and cron scheduler. One container. Same surfaces. Swap the brain — you don't fork this, you FROM it.
Updated -
On-demand WireGuard exit pools with short-lived SOCKS5 and HTTP proxy leases for self-hosted clients, containers, and Tailscale.
Updated -
Self-hosted speech server in one Docker image. OpenAI-compatible /v1/audio/transcriptions and /v1/audio/speech across 12 ASR models (Whisper, Parakeet, Canary, Sherpa-ONNX, Vosk) and 3 TTS engines (Kokoro, Qwen3-TTS voice cloning, Chatterbox Turbo). Live WebSocket ASR, file staging, MCP built in. CPU + CUDA images.
Updated -
A second brain for conversations you're already having: listens to your mic and system audio as two separate streams, transcribes both live, works out when the other side shut up, and hands you a reply draft before you panic. It drafts, never sends or speaks for you. Alpha — live capture is Linux/PipeWire only.
Updated -
Read Search Console, Bing Webmaster, GA4 and PageSpeed data through one self-hosted MCP server.
Updated -
proxq - The honey badger of HTTP proxies. Takes your request, throws it in a Redis-backed job queue, and deals with it when it damn well pleases. You get a job ID back instantly — come back later to pick up the goods.
Updated -
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.
Updated -
Interactive Brokers, curl-friendly — over REST + MCP. FastAPI + ib_async over a Linux-native IB Gateway: stocks/options/futures/forex/crypto/CFD contracts, quotes, historical bars, orders, positions, executions. Typed MCP tools mirror the whole surface. The IBKR half of mt5-httpapi — same shape, no Windows VM.
Updated -
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.
Updated -
Production-ready Docker image and GitLab CI build pipeline for Wanderer.
Updated -
Inspect, edit, and recompile what Hermes Agent has learned — a local-first observability and tuning layer for long-running agents.
Updated -
-
URL monitoring application. Probes your services every minute, displays 48-hour uptime history, and sends daily email recaps.
Updated -
Working with organisations and enterprises since 2000, we built Rediflow to answer a consistent need: one place for project flow (plan and track work packages, tasks, milestones, and capacity within each project), portfolio flow (demand and capacity across all projects and people), and one flow — a single source of truth. Update once, it flows everywhere. Planning, tracking, and reporting live in one place. Staff see their own allocations at a glance. Rediflow is purpose-built for capacity and portfolio planning — not a general-purpose ticketing system.
Updated -
Track AI spending across API providers, MCP tools, subscriptions, and self-hosted GPUs from your terminal. One CLI to see what you're actually paying — Anthropic, OpenAI, OpenRouter, vLLM on your own hardware — with real TCO math. Compare your self-hosted $/MTok vs cloud pricing. Local-first, no SaaS required.
Updated