Neura Market
IM.codes logo

IM.codes

Free

Mobile/web control layer for Claude Code, Codex, Gemini CLI, and other terminal-based coding agents.

FreeFree tier
Type
Open Source
Visit Website GitHub (38 stars)

About IM.codes

IM.codes is an open-source project that provides a shared memory layer and managed MCP tool surface for coding agents across multiple AI providers. It turns completed work into reusable context, injects or recalls the right history in future sessions, and supports agents like Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor, OpenCode, and Qwen. Features include terminal access, file browsing, git views, localhost preview, notifications, multi-agent workflows, native streaming output, and Apple Watch support. For spec-driven work, OpenSpec Auto Deliver handles change proposals through implementation, validation, and quality gates. The project also offers session sharing for collaborative coding, auto supervision for judging turns and audit/rework loops, and team discussion for multi-model review and audit to reduce single-model biases.

Key Features

Shared memory layer across coding agent sessions
Managed MCP tool surface for multiple AI providers
Cross-agent audit and supervised execution
OpenSpec Auto Deliver for spec-driven development
Multi-agent workflows with native streaming output
Session sharing for collaborative coding
Auto supervision with audit/rework loop
Team discussion for multi-model review and audit
Terminal access, file browsing, git views, localhost preview
Apple Watch support for quick session monitoring and notifications

Pros & Cons

Pros
  • Free and open-source
  • Supports a wide range of coding agents (Claude Code, Codex, Gemini CLI, GitHub Copilot, Cursor, etc.)
  • Provides shared context and memory across different AI providers and sessions
  • Includes mobile and Apple Watch access for monitoring and quick replies
  • Offers spec-driven automation with OpenSpec Auto Deliver
  • Enables collaborative coding and team review workflows
  • Built-in supervision and audit loops for quality control
Cons
  • Active personal open-source project, no warranty, SLA, or guarantee of stability or backward compatibility
  • May require technical setup and is not production-ready
  • Limited to terminal-based coding agents; no native desktop app (uses web/mobile interface)

Best For

Controlling coding agents remotely via mobile or web when away from deskSpec-driven development where changes are automatically delivered through proposal, audit, implementation, and quality gatesPair or multi-person collaborative coding around live agent sessionsMulti-model review and audit to reduce single-model misses, blind spots, and biases