phuryn/mini-harness
Agent
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 9 days ago.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A small agent harness for teaching, about 1,400 lines of Python with two dependencies. It runs a tool loop with local tools and web search, resumable sessions, compaction, Agent Skills, MCP servers, subagents, a /goal mode with a separate reviewer, and permission prompts with an…
Who it's for
Developers who want to learn how an AI agent harness is built, or who need a readable base for experimenting with agent tools and permissions
How to use it
Install
uv tool install git+https://github.com/phuryn/mini-harnessFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up phuryn/mini-harness in my project. Follow its README: https://github.com/phuryn/mini-harness. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/phuryn/mini-harness?ref=badge)Similar repos
- google-research/harness2
A Python framework for recursive agent harnessing, which refines the prompts, tools, memory, skills and orchestration around a fixed model. It runs a propose-probe-compose loop per task and keeps a pe
- IsuruMaduranga/harness-engineering-101
An open book series in Markdown that explains how AI agents work by building a roughly 300-line toy agent harness in plain Python. It covers the message array, tool calls, the agent loop, context mana
- YuhuaJiang2002/HarnessMM
Research implementation of HarnessMM, which reuses decisions an agent already made: a slow model call records future tool actions in a decision graph, and guarded checks on tool results decide whether
- pzs19/HarnessPro
A framework that recursively improves the harness of an AI agent (its instructions, tools and runtime policies) by diagnosing execution traces and selecting candidate changes with synthesized tests. O
- phuryn/product-engineering
A collection of agent skills for coding agents that guide a non-coding product person from first idea to paying users. Includes a start-here entry point, packs for building, shipping and running produ
- Open-RUA/uni-robot-agent
Open-source Python harness for robot-use agents that runs Codex or Claude Code runtimes against simulated robot environments such as RoboDojo, RoboUse and RoboLab. Includes a Python SDK, a local live