Agent harnessSoftware development

claude-harness

Scaffold a test-first harness for AI agents in any repo

Stars
3
Forks
0
License
MIT
Updated
Updated Jul 10, 2026

Checking live repository facts…

Project overview

Claude Harness scaffolds a repository-level working framework for AI-agent work. It creates concise rules, active and completed execution plans, lessons, and a technical-debt tracker, then uses failing tests to lock behavior before implementation. Review, phase-finish, and lesson-promotion steps keep the context current over longer projects, making it useful for new codebases, refactors, and durable maintenance.

Repository facts

Primary language
Not detected
License
MIT
Repository updated
Jul 10, 2026
Default branch
main

Resource types

Agent harnessPlugin

Use cases

Software developmentCode review and qualityProject and product managementTesting and debugging

Capabilities

Verification and evals

Audience

Developers

Related projects

Open claw-code
Agent harnessSoftware developmentLinux

claw-code

@ultraworkersRust

Build and inspect an agent-maintained Rust experiment around the `claw` CLI.

Stars
★ 194,695
Forks
⑂ 109,767
License
MIT
Open OpenHands
Agent harnessSoftware developmentClaude Code

OpenHands

@OpenHandsPython

Run, switch, and automate coding agents across local and remote backends.

Stars
★ 80,346
Forks
⑂ 10,253
GitHub updated
Jul 10, 2026
Open ruflo
Agent harnessSoftware developmentClaude Code

ruflo

@ruvnetTypeScript

Orchestrates agents, memory, tools, and automated workflows around Claude Code and Codex.

Stars
★ 63,849
Forks
⑂ 7,542
License
MIT
Open vibe-kanban
Agent harnessSoftware developmentClaude Code

vibe-kanban

@BloopAIRust

A coding-agent kanban and isolated-workspace tool that has announced it is sunsetting.

Stars
★ 27,323
Forks
⑂ 2,901
License
Apache-2.0
Browse more similar projects