IM.codes

English | 简体中文 | 繁體中文 | Español | Русский | 日本語 | 한국어

The IM for agents. Shared memory, OpenSpec Auto Deliver, managed MCP tools, supervised execution, and cross-agent audit across AI providers.

Two heads are better than one. But minds in concert don't answer fate, they author it. — 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, Codex, Gemini CLI, GitHub Copilot, Cursor, OpenCode, OpenClaw, Qwen, 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.

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.

Screenshots

Desktop

iPad / Tablet

Mobile

Apple Watch

Watch support covers quick session monitoring, unread counts, push notifications, and quick replies directly from the wrist.

Download

Supports iPhone, iPad, and Apple Watch. Also available as a web app.

Why

When you leave your desk, most coding-agent workflows fall apart. The agent is still running in a terminal, but continuing the work usually means SSH, tmux attach, remote desktop hacks, or waiting until you're back at your laptop.

That reach problem is only one half of it. Complex coding-agent work also needs steadier judgment: a single model can fall into familiar patterns, miss issues, or produce unstable answers on hard tasks. Switching providers can help, but without shared context it can also lose the thread.

IM.codes is built around both needs. It keeps sessions within reach from mobile or web: open the terminal, inspect files and git changes, preview localhost from another device, get notified when work finishes, invite another person into the same session or server, and keep multiple agents moving on your own infrastructure. It also pairs Shared Agent Context & Memory with Multi-Agent Discussions & Cross-Provider Audit: durable recall comes from summarized completed work, while Team discussion is structured cross-model review before code lands. It does not make output perfect, but it reduces single-model blind spots and helps complex work converge with more review.

It is not another AI IDE or a generic remote terminal. It is the messaging, memory, and review layer around terminal-based coding agents.

OpenSpec Auto Deliver

For OpenSpec-based changes, Auto Deliver turns a change folder into an end-to-end supervised delivery run: proposal/spec review, implementation, validation, Team audit, automatic module scoring, rework gates, and a visible final handoff.

• One-click change pipeline. Launch from an OpenSpec change on a transport-backed coding session. IM.codes resolves the owning session, locks the Team lane to prevent conflicting runs, reads tasks.md, and keeps a live run projection in the UI.
• Spec audit before implementation. Optional proposal/spec audit-repair uses the normal Team flow (default audit>review>plan) and reads an authoritative JSON result instead of trusting chat summaries.
• Task-driven implementation loop. The daemon sends focused implementation prompts back into the same session, works only on that OpenSpec change, tracks checked/unchecked tasks, and surfaces safe validation command candidates discovered from project manifests.
• Automatic module scoring. Every audit produces structured scores for spec, tasks, implementation, tests, and risk, with evidence and summaries visible in the run details instead of buried in chat text.
• Implementation audit and rework gates. The final scored verdict — PASS, REWORK, or BLOCKED — decides whether the run can pass, should repair while limits allow, or needs a human decision.
• Presets for delivery depth. fast, standard, strict, and deep tune spec-audit rounds, implementation-audit rounds, max implementation prompts, and elapsed-time limits.
• Fail-closed and human-owned. Auto Deliver asks for human input on invalid audit output, time/prompt limits, manual interference, incompatible Team state, or unreadable tasks. It does not stage, commit, or push code; the user stays the final release owner.

Collaborative Coding

Share a tab, sub-session, or whole source server with another user. Use viewer for read-only review or participant when a teammate should send prompts into the covered sessions. Shared messages carry actor labels, and access can be downgraded or revoked from the UI.

Shared Agent Context & Memory

IM.codes continuously turns completed agent work into reusable memory and feeds that context back into future sessions.

• Problem → solution memory, not log spam. Only final assistant.text outputs are materialized. Streaming deltas, tool calls, and intermediate noise are excluded.
• Personal memory with optional cloud sync. Raw and processed memory always stay local; processed summaries can optionally sync to a user-scoped cloud pool shared across your devices.
• Enterprise shared context. Teams can publish reusable memory into workspace/project scopes, inspect it in the UI, query it, and see stats instead of treating context as hidden prompt text. This part is still under active development and has not been fully production-tested yet.
• Multilingual recall. Local semantic search and server-side pgvector recall use multilingual embeddings, so related fixes can be found across English, Chinese, Japanese, Korean, Spanish, Russian, and mixed-language repos.
• Automatic injection where it matters. Relevant past work is injected both per-message and at session startup, with timeline cards that show what was recalled, why, the releva