alfranz/hush
Context-efficient command runner for coding agents.
This tool helps developers streamline the output of shell commands, especially when working with AI coding agents. It takes any shell command as input and provides a concise summary line (✓ for success, ✗ for failure) or a filtered output of errors and warnings. Software developers and anyone automating code-related tasks can use this to get clearer, more manageable feedback from build tools, linters, and test runners.
Use this if you are a developer or an AI coding agent who needs to quickly understand the outcome of shell commands without sifting through verbose output, particularly to reduce context for AI models.
Not ideal if you always need the full, unfiltered output of every command, or if you are not using AI agents that benefit from reduced context.
Stars
22
Forks
1
Language
Go
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/alfranz/hush"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
code-yeongyu/oh-my-openagent
omo; the best agent harness - previously oh-my-opencode
nrslib/takt
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and...
beclab/Olares
Olares: An Open-Source Personal Cloud to Reclaim Your Data
neomjs/neo
The Application Engine for the AI Era. A multi-threaded, AI-native runtime with a persistent...
rush86999/atom
Atom Agent, automate your workflows by talking to an AI — and let it remember, search, and...