Harnesses
Explore 38 reviewed agent harnesses and their verified capabilities.
Claude CodeAvailable on HarnessRouterAnthropic’s coding agent for understanding codebases, editing files, running commands and tests, and iterating on implementation tasks.
CodexAvailable on HarnessRouterOpenAI’s coding agent for building, reviewing, testing, and shipping software across local and cloud development environments.
Hermes AgentAvailable on HarnessRouterAn open-source, persistent AI agent with memory, reusable skills, built-in tools, browser automation, scheduled tasks, and subagents.
piComing soon on HarnessRouterA personal, extensible coding agent designed to be shaped around an individual developer’s workflow.
Agent ZeroReviewedAn open-source framework for creating and operating customizable autonomous AI agents.
AiderReviewedAn open-source AI pair-programming agent that works directly from the terminal.
ClineReviewedAn open-source IDE coding agent that explores codebases, edits files, runs terminal commands, and operates a browser.
CodebuffReviewedA self-improving command-line coding agent.
Command CodeReviewedA reviewed agent harness with source-backed interface and capability evidence.
ContinueReviewedA reviewed agent harness with source-backed interface and capability evidence.
CrushReviewedA reviewed agent harness with source-backed interface and capability evidence.
CursorReviewedA reviewed agent harness with source-backed interface and capability evidence.
Deep Agents CodeReviewedA reviewed agent harness with source-backed interface and capability evidence.
Factory DroidReviewedA reviewed agent harness with source-backed interface and capability evidence.- Gajae CodeReviewedA reviewed agent harness with source-backed interface and capability evidence.
gooseReviewedAn open-source, on-machine AI agent for extensible development and automation workflows.- jcodeReviewedA reviewed agent harness with source-backed interface and capability evidence.
JunieReviewedJetBrains’ agentic coding tool for reviewing, writing, and modifying code through IDE and terminal workflows.
Kilo CodeReviewedAn open-source coding agent for VS Code, JetBrains, and the command line, built around agentic development workflows.
MiMo CodeReviewedA reviewed agent harness with source-backed interface and capability evidence.
nanobotReviewedAn ultra-lightweight personal AI agent.
Oh-My-PiReviewedAn open-source, multi-provider coding agent designed for terminal-based software development workflows.
OpenClawReviewedAn open-source personal agent that connects to messaging apps and can browse, run commands, manage files, and take external actions.
OpenHandsReviewedAn open-source coding agent platform that can run commands, browse the web, edit software projects, and call APIs.
OpenSquillaReviewedA reviewed agent harness with source-backed interface and capability evidence.- Ottili CoderReviewedA reviewed agent harness with source-backed interface and capability evidence.
poolReviewedPoolside’s coding agent for terminal workflows and ACP-compatible editors.
PostQodeReviewedA reviewed agent harness with source-backed interface and capability evidence.
Qwen CodeReviewedA command-line AI workflow tool for coding and software engineering tasks.
QwenPawReviewedA reviewed agent harness with source-backed interface and capability evidence.
Roo CodeReviewedA VS Code agent with customizable modes for coding, architecture, debugging, and review across multiple model providers.
SkyvernReviewedA reviewed agent harness with source-backed interface and capability evidence.
stagewiseReviewedA reviewed agent harness with source-backed interface and capability evidence.
Swades AgentReviewedA reviewed agent harness with source-backed interface and capability evidence.
TeleClawReviewedA platform for creating custom Telegram AI bots.- VerdentReviewedA reviewed agent harness with source-backed interface and capability evidence.
Z CodeReviewedA reviewed agent harness with source-backed interface and capability evidence.
Zoo CodeReviewedA reviewed agent harness with source-backed interface and capability evidence.