L

llm

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.

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.

💬 Epic prompts to turbo-charge your LLM chatbots.

A unified Python interface to select and use multiple Large Language Model (LLM) providers through a common API.

Manage agents from anywhere.

Goal. Loop. Audit. Done. — a pi-coding-agent extension that supervises long-running work, with isolated auditor on each completion. Beat bamboozling by design: the auditor runs in a fresh session with no extensions, no skills, no editor — only the read tools needed to verify your goal.

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.

Context advisor for coding agents - injects relevant facts into your session and keeps them up to date

Ephemeral self-managed GitLab simulations on Google Compute Engine for LLM-mediated work.

OpenAI / OpenAI-compatible provider for the phpboyscout go/chat multi-provider AI client. · https://chat.go.phpboyscout.uk

Local-first, vision-LLM CAPTCHA solver for AI agents — MCP plugin + NopeCHA-style HTTP job API over any Chromium

Multi-provider AI chat client for Go — light, framework-free, opt-in per-SDK. Part of the phpboyscout Go toolkit. · https://chat.go.phpboyscout.uk

Compiler that turns Magic: The Gathering Oracle text into a typed AST and a symbolic, LLM-facing DSL (and back) for grammar-constrained card generation.

An LLM gateway for environments where the model provider is not your choice to make. One OpenAI-compatible endpoint in front of AWS Bedrock and on-device llama.cpp inference.

GitLab's official AI skills vendored for GDK-free environments, plus a no-GDK contribution spine. Sibling of gitlab-simulation.

Google Gemini provider for the phpboyscout go/chat multi-provider AI client. · https://chat.go.phpboyscout.uk

Anthropic Claude provider for the phpboyscout go/chat multi-provider AI client. · https://chat.go.phpboyscout.uk

Cognimatrix is an open source specification for distributed machine intelligence, providing a modular foundation for connecting datasets, knowledge, models, agents, tasks, and intelligent workflows. It preserves identity, provenance, rights, accountability, interoperability, and independent commercialization across the entire intelligence lifecycle. https://roxanneardary.com/cognimatrix/

Agent supervision, memory distillation, and multi-model orchestration. Kybernetes steers AI agents — catching hallucination and drift before they compound.

Unified AI chat client — Claude, OpenAI, Gemini, Ollama and compatibles behind one interface. Part of the phpboyscout Rust toolkit. · https://chat.rust.phpboyscout.uk