im4codes/imcodes

Registry

Summary

imcodes is an instant messaging platform designed for AI agents, providing shared agent context and memory, supervised execution, and cross-agent audit capabilities across multiple AI providers including Claude, OpenAI, Gemini, and Codex.

Key features

• Shared agent context and memory across AI providers
• Supervised execution for agent actions
• Cross-agent audit logging and monitoring
• Multi-provider support: Claude, OpenAI, Gemini, Codex
• Instant messaging interface for agent communication

Use cases

• Coordinating multiple AI agents in complex workflows
• Auditing and monitoring agent decisions across providers
• Building multi-agent systems with shared memory
• Supervising autonomous agent execution in production

README excerpt

# [IM.codes](https://im.codes) [English](README.md) | [简体中文](README.i18n/README.zh-CN.md) | [繁體中文](README.i18n/README.zh-TW.md) | [Español](README.i18n/README.es.md) | [Русский](README.i18n/README.ru.md) | [日本語](README.i18n/README.ja.md) | [한국어](README.i18n/README.ko.md) **The IM for agents. Shared memory, managed MCP tools, supervised execution, and cross-agent audit across AI providers.** > Two heads are better than one.<br> > But minds in concert don't answer fate, they author it.<br> > — IM.codes IM.codes gives coding agents one shared memory layer and one managed MCP tool surface across providers. It turns completed work into reusable context, then injects or recalls the right history in future sessions across [Claude Code](https://github.com/anthropics/claude-code), [Codex](https://github.com/openai/codex), [Gemini CLI](https://github.com/google-gemini/gemini-cli), GitHub Copilot, Cursor, OpenCode, [OpenClaw](https://openclaw.com), [Qwen](https://github.com/QwenLM/qwen-agent), and more — with terminal access, file browsing, git views, localhost preview, notifications, multi-agent workflows, and native streaming output for transport-backed agents. Built-in Auto supervision can judge completed turns, continue work autonomously, and optionally run an audit/rework loop before handing control back. Team discussion lets multiple models review and audit each other's plans and implementations — an effective way to reduce single-model misses, blind spots, and biases. > **Disclaimer:** This is an actively developed personal open-source project. There are no warranties, no SLA, and no guarantees of stability, security, or backward compatibility. Use at your own risk. Breaking changes may happen at any time without notice. ### Breaking Changes - **PostgreSQL default im

Topics