Wispr Flow: Dictation That Works EverywhereStop typing. Start speaking. 4x faster.
Promoted
Mozzie
Codex Claude Gemini CLI parallel agents orchestration
64 followers
Codex Claude Gemini CLI parallel agents orchestration
64 followers
Mozzie is a local-first desktop tool that lets you orchestrate multiple AI coding agents in parallel. Create work items, spawn agents, and manage their execution from a single workspace. Each agent runs in its own terminal while Mozzie tracks tasks, context, and results. Mozzie works with existing coding agents like Codex, Claude Code, and Gemini CLI — it doesn’t replace them, it coordinates them. Open source on GitHub.
Mozzie
OpenOwl
This solves a real pain point. I've been juggling 3-4 Claude Code terminals for different parts of the same project and it gets chaotic fast. The parallel agent orchestration with a single workspace view is exactly what's needed. Quick question: does it handle conflicts when two agents try to edit the same file?
Mozzie
@mihir_kanzariya Not automatically. The way I’m approaching it is to prevent that upfront rather than try to recover later. Each work item runs in its own git worktree/branch, but if two agents edit the same file, that can still create a merge conflict. So the orchestrator is meant to split work into non-overlapping file ownership, put shared files into a foundation task first, and use dependencies when something has to land, dependent tasks are auto launched when foundations are met.
Congrats on your launch! @builder_xc Great initiative here! Are work items defined manually by the developer, or is there any intent to let Mozzie break down a higher-level spec (e.g., a feature brief or a GitHub issue) into subtasks and auto-assign them to respective agents?
Mozzie
Thanks @jacklyn_i , the intent is to run everything through the orchestrator, which breaks a spec into work items or sub work-items if needed, auto assigns agents and runs them in parallel - the preferred way. Manual actions are optional.
Love the multi-agent orchestration approach! I've been building viruagent-cli which
gives AI agents access to social platforms via CLI — the idea of agents running in
parallel resonates a lot. How do you handle context sharing between agents?