Dapols
PlansAI vs hiringPricingToolsBenchmarksBlog
Sign inFind my AI workflow
Dapols

The job big companies pay a forward-deployed engineer six figures to do — as a tool, for two figures.

Join the price-watch list

Verified from vendor pages. We're not sending emails yet — leave your address and you'll be first when we do.

Product

  • AI Deployment Plans
  • AI Plan Finder
  • AI skills library
  • AI tools
  • Pricing

Explore

  • AI vs hiring
  • Stack cost checker
  • ROI calculator
  • Works with your tools
  • Comparisons
  • Alternatives
  • By industry
  • By budget

Offerings

  • AI Deployment Plans
  • Bigger or more complex? Tell us.
  • Bigger or more complex?

Company

  • Blog
  • AI model tracker
  • Submit a tool
  • Contact
  • Privacy
  • Terms of Service

Trust & methodology

  • About
  • Methodology
  • How we rank AI tools
  • Forward-deployed AI
  • Affiliate disclosure
  • AI tool pricing updates
  • AI price index
  • Security & data privacy

© 2026 Dapols. All rights reserved.

support@dapols.comX

Put AI to work—one measurable workflow at a time.

Coding harnesses

The coding agent is not the model

You pick a model for capability and a harness for how the work gets done. These are the harnesses worth knowing in 2026, with every claim sourced and dated — including the one that has already been retired.

Compare themAll rows verified Aug 14, 2026

Read this first

A harness is the client that turns a model into an agent: it holds the loop, the tools, the file access and the permissions. Two people using the same model through different harnesses get very different results — and pay very different amounts, because the harness decides how many tokens the job costs.

One of these is already gone

Google retired Gemini CLI into Antigravity CLI, and consumer access stopped serving requests on 18 June 2026. We keep the row because knowing what replaced it is more useful than a page that quietly drops it.

Labs benchmark through harnesses now

When Z.ai published GLM-5.3's scores, it ran them inside Claude Code — a competitor's harness. That tells you the harness layer has become standard infrastructure, and that a model's published score is partly a statement about the client it was measured in.

Compare the harnesses

Filter by how each one handles models, then select a row for its full detail, limitations and sources. Retired harnesses are hidden by default.

HarnessModelsLicenceRuns onPricing
AnthropicLocked to one vendorAnthropic models only (Claude Fable, Opus, Sonnet, Haiku)ProprietaryTerminal, VS Code, JetBrains, Desktop, Web, GitHub, SlackIncluded with Claude paid plans; also usage-billed via the Anthropic API
SSTAny modelAny provider via BYOK — Anthropic, OpenAI, Google, DeepSeek, GLM, local modelsOpen sourceTerminal, IDE extensions, WebFree and open-source with your own API keys; OpenCode Go plan $5 first month, then $10/month
Z.aiOwn model, not lockedGLM family (GLM-5.3, GLM-5.2), including a self-hosted GLM endpointProprietaryDesktop (macOS, Windows, Linux), Mobile steering via WeChat / FeishuVia the GLM Coding Plan's points quota — off-peak calls cost 50% of standard points
LangbaseAny modelAnthropic, OpenAI, Google, DeepSeek, Qwen, Kimi, GLM, MiniMax and more — BYOK with no markupProprietaryTerminalFrom $1/month with $10 credits, up to $200/month Ultra; Teams $40/month; BYOK carries no markup
DeepSeekOwn model, not lockedBuilt around DeepSeek models (V4 Flash, V4 Pro); plugin architecture allows othersOpen sourceTerminal, Web UIMIT-licensed and free; you pay only for model tokens
GoogleOwn model, not lockedGemini modelsProprietaryDesktop, CLI, SDKVia Google AI Pro / Ultra and Gemini Code Assist licences

Claude Code

Anthropic
Used as the reference harness by other labs
Z.ai ran its own GLM-5.3 benchmarks inside Claude Code 2.1.207 — including Terminal-Bench, CyberGym and SWE-Marathon Source
Extension surface
Skills, hooks, subagents, plugins, MCP servers and scheduled tasks Source

Extension points

  • SupportedSkills
  • SupportedHooks
  • SupportedSubagents
  • SupportedPlugins
  • SupportedMCP

The honest limitation

Model-locked. You cannot point it at a cheaper open-weights model when a task does not need a frontier one.

Best for

Teams already on Anthropic models who want the most tuned, best-integrated experience.

Source Verified 2026-08-14

Questions people actually ask

What is an AI coding harness?
The client that turns a language model into an agent. It runs the loop, exposes tools like file editing and the terminal, manages context and permissions, and decides when the task is done. The model supplies the reasoning; the harness supplies everything else.
Does the harness change how much I pay?
Substantially. The harness controls how much context it re-sends, whether it caches, and how many turns it takes. Two harnesses running the same model on the same task can differ several-fold in output tokens, and output tokens are most of the bill.
Can I use one harness with several model providers?
Yes, if you choose a model-agnostic one. OpenCode and Command Code both let you bring your own keys across providers. Claude Code is locked to Anthropic models; ZCode and Antigravity are built around their vendor's models.
Is Gemini CLI still usable?
Not on consumer plans. It stopped serving requests on 18 June 2026 for Google AI Pro and Ultra subscribers and free Gemini Code Assist users, and was replaced by Antigravity CLI. Access under Code Assist Standard or Enterprise licences was unaffected.

A harness choice is downstream of a model choice.

Pick the model that clears your quality bar at the lowest cost, then pick the harness that runs it the way your team works. Doing it the other way round is how people end up locked into a vendor they did not mean to choose.

What shipped recently

Dated releases from every major lab, with each vendor's own claims labelled as claims.

Open

Independent scores

Third-party benchmark results — deliberately separate from whatever a lab publishes about itself.

Open

What to actually build

A deployment plan picks the stack for one workflow at your budget, models and tooling included.

Open

We record a source and a check date for every claim on this page, and we show disagreements instead of resolving them silently. How we verify