"Information on MCP-Codex-Keeper" matching MCP servers:

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.

Public read-only registry for Codex-compatible animated companion packs. Search approved pets, fetch install instructions, generate badges and embed cards, and discover the pet request flow via Streamable HTTP MCP.

Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.

A tiny MCP server that wraps Perseus Vault to provide persistent, encrypted, local-first memory for OpenAI Codex agents, enabling them to remember project conventions, decisions, and context across sessions.

On-chain delivery receipts for x402 AI-agent payments on Solana: anchors SHA-256 digests of delivered content to a PDA after settlement; buyers verify proof of delivery offline with zero trust in the seller. Live MCP endpoint + npm bridge.

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

Local security layer for coding agents: keeps secret values out of what Claude Code, Codex CLI, Cursor and OpenCode send to their model, and checks untrusted text for prompt injection. MIT, runs on your machine, no account.

Enables calculation of the 2025-2028 federal overtime, tips, and senior deductions — applying IRS caps, MAGI phase-outs, and bracket tables — plus eligibility explanations and estimated federal tax savings.

Enables persistent, project-scoped memory for OpenAI Codex Desktop and CLI on Windows, capturing prompts and responses through managed hooks, with federated recall across projects and optional local graph extraction.

Local ledger for development ports: leases a block of ports per project slot (one per working copy), renders env files, and resolves service names to URLs. No daemon, no listener.

Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions

An MCP bridge that enables AI coding agents to delegate implementation tasks to the OpenAI Codex CLI, allowing the orchestrator to plan and review while Codex executes.

Add OpenAI (Codex) models to Claude code

Provides read-only Codex consultation tools over MCP, enabling fresh threads, continuation, and project reviews via local stdio.

Two-way MCP bridge between Claude and Codex: send prompts into a live Codex Desktop thread and messages into a running Claude Code session, keeping each conversation in its own app. Native Desktop tasks on Windows and macOS; CLI/app-server mode on Linux and WSL.

Enables local Laya-MLX typed decisions (classification, scoring, risk routing, and yes/no) for coding agents like Codex, Claude Code, DeepSeek Harness, and Pi via MCP, running entirely on Apple Silicon Macs.

Enables OpenAI Codex to inspect and operate Windows desktop applications in the background while the user keeps control of the mouse, keyboard, and foreground window, with each action verified against the application's real state.

让两个 AI 在同一个对话里替你互相把关

Enables a Chief of Staff client to find Codex tasks, create and submit project work with exact prompts, track progress via durable receipts, and continue or manage the same conversation locally.

Enables lossless context management for OpenAI Codex CLI by capturing and compressing conversation history in SQLite, with lexical recall via MCP tools.