Alexandria LLM API Gateway unifies multiple AI subscriptions into a single local endpoint
Alexandria is a local daemon that consolidates AI subscriptions (Claude Max, ChatGPT/Codex, SuperGrok, Gemini) into one OpenAI/Anthropic-compatible endpoint on 127.0.0.1:4100. It provides a credential vault, automatic token refresh, model routing, format translation, full trace capture, and usage/limit tracking, allowing any coding harness to authenticate and bill correctly.
Entities
Related
Multi-LLM desktop app with cross-platform conversation handoff
A free, local desktop app that lets users run Claude, ChatGPT, Gemini, and Copilot side by side, including multiple accounts of the same platform. When hitting a usage limit on one, the entire conversation can be transferred to another platform's input box with a 'take over' instruction, allowing seamless continuation.
Coder: CLI tool to delegate coding tasks to background LLM agents
Coder is a CLI/plugin that lets developers dispatch coding tasks to background agents powered by Claude CLI or Codex CLI. It keeps the main session context clean and distributes workload across existing subscriptions. Built entirely with Claude Code, it is free and open source.
Passation: Resume interrupted AI coding sessions seamlessly
Passation is a passive Python script that generates a handoff document when a Claude Code or Codex CLI session is interrupted by usage limits. It captures the current state, unfinished tasks, and plans so a new agent can continue without losing context. This solves the problem of coding sessions dying mid-task and the risk of switching agents.
quota-axi: CLI tool aggregates LLM quota windows for agents
quota-axi is a CLI tool that reports quota windows for Claude, Codex, Cursor, GitHub Copilot, and Grok in a single AXI-shaped call. It is designed to give agents awareness of subscription quotas before deciding where to run work, without routing, recommending, or proxying.
Inkfold – workspace across multiple AI providers with shared memory
Inkfold is a workspace that lets users interact with multiple AI providers (e.g., OpenAI, Anthropic) through a unified interface, with a shared memory system that persists context across sessions. It solves the problem of managing separate chat histories and contexts when using different AI models, providing a seamless experience for power users and developers.

