A chat interface for AI coding agents — control Claude Code, Codex, Gemini CLI, OpenCode from browser and mobile
How to install imcodes?
im4codes/imcodes
$git clone https://github.com/im4codes/imcodesInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install imcodes by running `git clone https://github.com/im4codes/imcodes`, then use it for the current task and follow its documentation at https://github.com/im4codes/imcodes.
README.md
| 1 | # [IM.codes](https://im.codes) |
| 2 | |
| 3 | [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) |
| 4 | |
| 5 | **The IM for agents. Shared memory, OpenSpec Auto Deliver, managed MCP tools, supervised execution, and cross-agent audit across AI providers.** |
| 6 | |
| 7 | > Two heads are better than one.<br> |
| 8 | > But minds in concert don't answer fate, they author it.<br> |
| 9 | > — IM.codes |
| 10 | |
| 11 | 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. For spec-driven work, OpenSpec Auto Deliver can take a change from proposal/spec audit through implementation, validation hints, Team audit/rework, automatic module scoring, and final quality gates. Session sharing also supports pair or multi-person collaborative coding around live agent sessions. 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. |
| 12 | |
| 13 | > **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. |
| 14 | |
| 15 | ## Screenshots |
| 16 | |
| 17 | ### Desktop |
| 18 | |
| 19 | <p> |
| 20 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-sidebar.png"><img src="landing/imcodes-sidebar.png" width="24%" /></a> |
| 21 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes0.png"><img src="landing/imcodes0.png" width="24%" /></a> |
| 22 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes1.png"><img src="landing/imcodes1.png" width="24%" /></a> |
| 23 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes2.png"><img src="landing/imcodes2.png" width="24%" /></a> |
| 24 | </p> |
| 25 | |
| 26 | ### iPad / Tablet |
| 27 | |
| 28 | <p> |
| 29 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-ipad2.png"><img src="landing/imcodes-ipad2.png" width="48%" /></a> |
| 30 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-ipad3.png"><img src="landing/imcodes-ipad3.png" width="48%" /></a> |
| 31 | </p> |
| 32 | |
| 33 | ### Mobile |
| 34 | |
| 35 | <p> |
| 36 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-m6.png"><img src="landing/imcodes-m6.png" width="18%" /></a> |
| 37 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-m7.png"><img src="landing/imcodes-m7.png" width="18%" /></a> |
| 38 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-m8.png"><img src="landing/imcodes-m8.png" width="18%" /></a> |
| 39 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-m5.png"><img src="landing/imcodes-m5.png" width="18%" /></a> |
| 40 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-m1.png"><img src="landing/imcodes-m1.png" width="18%" /></a> |
| 41 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-m2.png"><img src="landing/imcodes-m2.png" width="18%" /></a> |
| 42 | <a href="https://raw.githubusercontent.com/im4codes/imcodes/master/landing/imcodes-m3.png"><img src="landing/imcodes-m3.png" width="18%" /></a> |
| 43 | <a href="https: |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
