mereyabdenbekuly-ctrl/clodex-ide

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

What it solves

CLODEx is designed for long-running engineering tasks that typically exceed the scope of a single chat session. It replaces the disposable chat-first workflow with a durable workspace where task history, context, and environment state are preserved across restarts, preventing the need to rebuild context from scratch.

How it works

It integrates multiple engineering tools into a single local-first desktop workspace. This includes a code editor, Git integration, a terminal, and an embedded browser. The system uses an agentic approach where the AI proposes plans and actions, which the user must then review and approve through dedicated surfaces for "Pending Edits" and line-level diffs. It supports a wide range of model connections, including CLODEx accounts, bring-your-own-key (BYOK) providers, OpenAI-compatible endpoints, and local inference via Ollama.

Who it’s for

Software engineers who need an AI-powered IDE that maintains state for complex, multi-step changes across a repository, and who prefer local-first control and explicit review of AI-generated changes.

Highlights

  • Durable Workspaces: Maintains task history and workspace-aware context across sessions.
  • Integrated Tooling: Combines files, Git, terminal, and browser in one environment.
  • ** uma MCP Support:** Supports user-configured stdio and remote MCP servers with approval-aware execution.
  • Model Flexibility: Compatible with hosted providers and local Ollama instances.
  • Review-Centric Design: Explicit permission prompts and diff surfaces ensure model output is treated as input, not authority.

Related

  • Project
    clawwork-ai/ClawWork

    A local-first workspace client for OpenClaw that replaces chat-based agent interfaces with a structured, task-oriented environment for managing parallel AI agent sessions and artifacts.

  • Project
    maddada/Ghostex

    A native desktop workspace for managing multiple CLI AI agents, featuring integrated terminals, a built-in IDE, and mobile access to live sessions.

  • Project
    Kc1t/alethe-agents

    A local-first desktop workspace for running multiple AI coding agents and shells side-by-side with persistent sessions and shared MCP server management.

  • Project
    DY-2026/GameDesignOS

    A local-first operating layer for AI-assisted game design that transforms fragmented AI output into structured, evidence-linked design decisions and project memory.

  • Project
    holaboss-ai/holaOS

    An agentic workspace that integrates AI agents side-by-side with real applications and chat tools, featuring local-first memory and shared tool access.