# Mica - Agent-First Builder Experiment

**URL:** <https://forums.developer.nvidia.com/t/mica-agent-first-builder-experiment/371394>\
**Category:** DGX Spark / GB10 Projects\
**Tags:** developer, tools, spark, llama, agentic-ai\
**Created:** [May 26, 2026, 10:47pm UTC](https://forums.developer.nvidia.com/t/mica-agent-first-builder-experiment/371394 "2026-05-26T22:47:10Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rob.chang](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/rob.chang/32/465044_2.png) [@rob.chang](https://forums.developer.nvidia.com/u/rob.chang)\
**Post date:** [May 26, 2026, 10:47pm UTC](https://forums.developer.nvidia.com/t/mica-agent-first-builder-experiment/371394/1 "2026-05-26T22:47:10Z")

</div>

Hi All - I’ve been exploring what’s possible with agentic tools running locally on the DGX Spark and am sharing my latest experiment: Mica, a workspace where you interactively collaborate with multiple agents — voice, coding, and general — to build and run apps.

Compared to other coding agents, Mica helps you and agents curate and manage context for a project on a shared _Canvas_, instead of primarily within a chat session. This is useful when building apps, when you and the coding agent(s) need to align on scope, functionality, dependencies, and implementation approach.

 ![solar](https://global.discourse-cdn.com/nvidia/original/4X/c/c/8/cc898ff1172ed57f840bcb9f4b4a43fa800a04f1.jpeg)

A few things I’m exploring with Mica:

- Project materials stay as plain files that any tool can read or modify, while Mica renders them as rich _Cards_ that make the meaning and structure easier to work with.

- Specs, scope, dependencies, implementation notes, and outputs stay visible and adjust as the project evolves.

- Runnable Cards as the output: dashboards, visualizers, document tools, workflow UIs, and scripts.

- Multiple local agents working alongside local voice input/output. Current setup: Qwen3.6-35B, Parakeet STT, Kokoro TTS, OpenCode, Qwen Code, and Claude Code agents.

- Modern local inference in the loop: vLLM, NVFP4, speculative decoding, and llama-server support.

- A local-first workflow that can run on DGX-class hardware, smaller GPU setups, or cloud endpoints when needed.

- Long-running project workspaces that stay available across devices, so you can keep multiple agent builds moving in parallel and drop back in from a laptop, tablet, or phone.

Mica runs in Docker and comes set up for both vLLM and llama-server inference. You can also point it to cloud endpoints when you want to compare models or use cloud inference.

Check it out here: [https://github.com/mica-agent/mica](https://github.com/mica-agent/mica)

Cheers,

Rob
