← Browse tools

Agent frameworks

OpenHarness

A Python agent harness with tool execution, skills, memory and multi-agent coordination, plus the built-in ohmo personal-assistant application.

15,763 stars

Overview

Research summary

OpenHarness supplies the infrastructure around a language model that turns individual completions into an agent workflow. Its documented capabilities include tool-call loops, skill loading, persistent context, permission controls, hooks, and coordination between multiple agents. The repository also includes ohmo, a personal-assistant application built on the same foundation and reachable through supported communication channels.

This distinction matters: the reusable harness is the core building block, while the assistant is one way of using it. Integrating an existing model or coding-agent subscription does not transfer control over provider access or eliminate the need to configure permissions. Operators should review the files, commands, credentials, and external services available to each workflow.

The Python implementation is MIT licensed, with model services, channels, and other external integrations governed separately.

Repository summary

Stars
15,763
Open issues
Unavailable
Last push
2026-06-04
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Implementation

Recorded implementation details and interfaces for OpenHarness.

Implementation details

Python agent harness and ohmo assistant with terminal interfaces

Languages
Python
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

HKUDS/OpenHarness ↗

Stars
15,763
Open issues
Unavailable
Last push
2026-06-04
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06
Stars source
Recorded fallback
Last push source
Recorded fallback

Documentation

Recorded references and research provenance for this entry.

Recorded sources 4

Research metadata

Research date
2026-09-16
Catalogue snapshot
2026-10-06