agency-agents vs Harness²: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of agency-agents and Harness² — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
a
agency-agents
msitarzewski
Open-source collection of specialized AI agent personalities installable into Claude Code, Cursor, Codex and more.
Key features
- Specialized Agent Roster: Role-specific agents with deep domain expertise rather than generic prompt templates.
- Personality-Driven Design: Each agent has its own voice, communication style and approach.
- Deliverable Focus: Agents define real code, processes and measurable outcomes.
- Desktop Installer App: A native app for macOS, Linux and Windows installs agents with a click and auto-updates.
- Multi-Tool Support: Works with Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Qwen, Windsurf and others.
- Selective Installation: Install only the divisions or teams you need.
Best for
- A developer installs a frontend specialist agent into Claude Code for UI work.
- A founder assembles a virtual agency of marketing and product agents.
- A team uses agent files as reference for writing its own agent prompts.
- A user installs the same roster across Cursor and Codex with the desktop app.
- A community manager adapts a community-focused agent for social outreach.
- A contributor submits a new specialized agent through a pull request.
H
Harness²
Google Research
Google Research's open-source framework for recursive agent harnessing that refines an agent's prompts, tools and memory per task.
Key features
- Task-Level Recursion: A contrastive Propose-Probe-Compose step proposes edits, probes their effects on the same task and composes a refined harness without ground-truth feedback.
- Harnessing-Level Recursion: A persistent improvement harness is updated with adopted harnesses and evidence-supported lessons from each task.
- Eight Editable Components: Exposes system prompt, guardrails, memory, tool guidance, subagents, skills, scripts and plugins as tunable parts.
- Parallel and Sequential Modes: Scale the task-level recursion budget by exploring candidates in parallel or refining sequentially.
- Multiple Executors: Run refinement with OpenCode and Codex executors.
- Built-In Benchmarks: Setup and run commands for JobBench, LAB (legal work) and WorkBuddy Bench (office, web and code).
- Credential-Free Demo: A local demo with deterministic editors runs both recursion modes without model credentials.
Best for
- Agent Harness Research: Study how contrastive harness edits affect agent performance across benchmarks.
- Improving Base Agents: Raise results of models such as GLM 5 and Gemini 3.5 Flash over their default harnesses.
- Professional Task Evaluation: Evaluate agents on legal, office and coding tasks using bundled benchmark guides.
- Tuning Coding Agents: Refine system prompts, skills and subagents for OpenCode or Codex executors.
- Reproducible Experiments: Run, judge and report benchmark experiments with resume support.