v0.1.2-alpha · DeepSeek setup + local Qwen productivity

MA

DeepSeek in minutes. Local small models turned into real productivity.

Developers want less setup pain, lower token pressure, and local models that actually finish repo work. MA delivers that: brainless DeepSeek onboarding, LM Studio/Qwen hardening, long-context agent loops, built-in tools, and benchmark evidence.

Download alpha View source

95.3% L2 pass rate proving local Qwen productivity

DeepSeek interactive setup without hand-written config

262K ctx context detection, usage display, output compression

Small-model tuned Qwen/LM Studio fixes are release gates

The Product Is The TUI

Model, tools, task state, context, and shortcuts are visible while the agent works.

MA terminal UI showing local Qwen model, MCP tools, input prompt, shortcuts, and context usage

First Run Matters

LM Studio local or DeepSeek official: same guided setup, no handwritten JSON.

The first screen is deliberately boring in the best way: arrow-key provider choice, sensible defaults, credential names, Keychain storage for remote keys, then model discovery.

MA init setup flow for LM Studio local and DeepSeek official providers

What Users Actually Want

Less friction, lower cost, more usable local intelligence.

“Do not make me configure this twice.”

ma init gives DeepSeek and LM Studio the same guided path: discover models, store credentials, create profiles, start working.

“Do not burn tokens for every loop.”

Local Qwen through LM Studio becomes the default place for repeated repo work, while DeepSeek stays one command away.

“Make my small model less dumb.”

Sampling passthrough, tool-call recovery, multimodal payload compatibility, and message integrity tests target Qwen/LM Studio behavior directly.

“Let it work for a long time.”

MA detects context windows, shows usage, compresses output, and is built for long agent loops rather than short chat demos.

“Do not leak my API key.”

Remote keys live in macOS Keychain, with config files storing references instead of plaintext secrets.

“Show me what the agent is doing.”

The TUI surfaces model, endpoint, tools, task progress, thinking state, session controls, and context budget while work is happening.

Benchmark As Evidence

The claim is not “we support local models.” The claim is “local small models can produce.”

The benchmark is proof that MA's small-model engineering matters: local Qwen3-30B, LM Studio, tools, long multi-turn repo tasks, 70-task alpha gate. It is not a generic leaderboard. It is evidence for the product promise.

Read benchmark details

RuntimeLM Studio

ModelQwen3-30B local

Tasks70

L0100%

L198.7%

L295.3%

Install

Download, extract, run.

macOS / Linux

tar -xzf ma-*.tar.gz
cd ma-*
./ma init
./ma

Windows

Expand-Archive ma-*.zip
cd ma-*
.\ma.cmd init
.\ma.cmd