← All categories

AI coding agents

Create, edit and troubleshoot digital projects.

Find your next useful agent

89 products · sources linked
Filters

Browse alphabetically. Open a product to see its sources and limits.

How to choose

Choose your coding environment

Browse all tools →

Compare browser builders, editor assistants and terminal agents around the code you have and how you review changes.

Build in the browser

Start a web app from a brief without installing a local editor. Check deployment, account requirements and export before committing.

Before choosing Confirm code export and budget for hosting, databases and connected services.

Work in your editor

Work with an existing project inside an editor. Compare supported environments, project context and the way you review changes.

Before choosing Inspect the diff and run project checks; a generated change is not a verified fix.

Work in the terminal

Use a coding agent alongside a repository and command-line tools. Check installation, model access and action approvals.

Before choosing Review command permissions, generated patches and model usage costs.

Inspect a recorded bug-fix task →

How you can start with these products

89 listed products, by how you can start

  • Free access6067%
  • Free trial22%
  • Paid1315%
  • Pricing not verified1416%

Free access can still involve paid model usage, hosting or connected services. Check each product's pricing notes.

Most-searched products in this category

Estimated monthly Google organic search traffic · 2026-10

ProductEstimated visits
Gemini CLIgeminicli.com · 2026-101.5M
Cursorcursor.com · 2026-101.1M
Google Antigravityantigravity.google · 2026-10917.2K
Apifyapify.com · 2026-10892.7K
Lovablelovable.dev · 2026-10716.7K
OpenCodeopencode.ai · 2026-10425.9K
Bolt (StackBlitz)bolt.new · 2026-10168K
Browserbasebrowserbase.com · 2026-10138K

Estimates cover each whole website and reflect how many people find it through Google, not usage, revenue or quality. Products that share a domain or sit on a page of a larger company site are left out. Products without an estimate are left out.

Keep exploring this workflow

Choose an editor, terminal agent or app builder. Compare workflows and inspect a recorded bug fix.

Start with your code, not a leaderboard

An IDE assistant fits work inside an existing editor. A terminal agent works directly with a repository. A browser builder helps start a new app. Choose the working environment before comparing model names.

Check what you can take with you

For a new site, inspect source export, hosting and database dependencies. For an existing project, start on a branch, describe a reproducible issue and ask for a focused patch with validation.

Which is the best AI coding agent for your workflow?

There is no single winner across new apps, existing repositories and team environments. For an editor workflow, compare Cursor, GitHub Copilot and Cline. For terminal work, compare Claude Code, Codex, Aider and Pi. For browser-based app building, compare Lovable, Replit and Bolt. Run the same small task before committing to a paid plan.

Free AI coding agents: what is actually free?

Separate the client license, model inference and hosting. A free installation does not establish a free end-to-end task. Check the model provider before running a large repository.

Open-source clients with separate model costs

These options let you choose model access; budget for provider usage or your own local compute.

  • Cline

    An open-source coding agent for an editor workflow.

    Before choosing
    Choose credits, your own provider keys or local compute; review commands before they run.

    Pricing and billing details

    Open-source client is free. Model inference is billed separately through credits or your own provider keys; local models require your own compute. Enterprise options are available.

    Official pricing ↗

    Pricing checked:

  • Aider

    An open-source terminal tool for working on a codebase.

    Before choosing
    Connect an API or local model and review the resulting Git changes.

    Pricing and billing details

    Open-source tool; you pay only for the LLM API or local model you connect.

    Official pricing ↗

    Pricing review pending

  • Pi Agent

    An open-source terminal coding agent.

    Before choosing
    The client has no bundled all-in free model allowance; confirm your provider or local setup.

    Pricing and billing details

    The open-source client is free to install. Model access is separate: a provider subscription, API usage or local-model compute can have its own cost. Pi does not establish an all-in free model allowance.

    Official pricing ↗

    Pricing checked:

  • OpenCode

    A coding client for terminal, desktop and IDE workflows with model choice.

    Before choosing
    The client is free; Go subscriptions and other model costs are separate. Check usage limits and approval settings.

    Pricing and billing details

    Free open-source client with some free models. Optional OpenCode Go costs USD 10/month; Go Plus costs USD 40/month per subscribing workspace member. Other providers or local compute have separate costs.

    Official pricing ↗

    Pricing checked:

Run a small cost check first

  1. Use a sample repository, set a provider spending limit where available, and record model usage for one accepted change.
  2. A hosted free tier may be easier to start with, but its message, credit and deployment limits are separate. Compare those limits on each product page.
Compare browser app builders →

Check the cost of one accepted coding task

Before a long run, separate three things: the cost shown by the client, the usage billed by the provider, and the rule that actually stops spending. A warning or a token counter does not establish a hard cap.

What the tools report
  • Cline

    Cline shows an estimated task cost that updates after API requests. Reconcile it with the selected provider’s bill; it is not a guarantee of the final charge.

  • Aider

    Aider’s /tokens command reports the current chat context. It is not a total of every billed request or retry in the task.

  • OpenCode

    OpenCode Zen documents monthly usage limits separately from automatic balance reloads. An enabled reload can charge more than the usage limit; check both controls in your account.

Verify a spending stop before relying on it

  1. List every billable service: the model provider, hosting, storage and any API the generated code calls. A limit on one service does not cover the others.
  2. Record whether the configured threshold blocks new usage or only sends an alert. Check its scope, reset period, reporting delay and any automatic top-up or paid fallback. If the stopping behavior is unknown, do not assume the run is capped.
  3. Use a sample repository and one acceptance test. Check the stop behavior in a sandbox or documented test mode where available; do not deliberately exhaust a paid allowance or interrupt production to test it.

Record all attempts, then judge the result

  1. Keep the same input, model settings and acceptance criteria when comparing tools. Record failed attempts, retries, human edits and test results as well as the final output.
  2. Keep client estimates, billed usage and cash top-ups in separate columns. A balance purchase is not the same as usage consumed. If a subscription does not expose a per-task charge, record it as unknown rather than inventing a dollar cost.
  3. Compare total billed usage across all attempts per accepted result, and report any unfinished task separately. A cheaper run that fails your acceptance test is not an equivalent result.

Download the blank cost-check worksheet

Blank template only: no benchmark results, preset prices or product ranking. Fill it locally; this page does not upload the worksheet or its contents.

Official documentation reviewed on 2026-10-05. These are documentation checks, not hands-on product tests.

Agent alternatives

Fix bugs in an existing project

Give a coding agent a reproducible problem and review the changes it makes.

01 / Prepare

A repository, reproduction steps and expected behavior

02 / Expect

Code changes and test results

03 / Review

Review the diff and rerun relevant tests. Generated code is not a security guarantee.

How to choose

Choose based on repository access, local editor versus cloud execution, and how much control you need over command execution.

Before you start

  1. Create a branch or backup.
  2. Provide the error and reproduction steps.
  3. List the tests that should pass.

Claude Code

Agentic coding that plans, writes code, runs tests, and opens pull requests.

Coding Agents & App BuildersPaidBuild a website+1
Details & limits

Why it fits Claude Code can work with an existing codebase to propose and review code changes for a reproducible problem.

PrepareAn accessible repository and reproduction steps

GetProposed code changes and an explanation

ReviewReview the diff and run your project tests

Keep in mindRequires a paid Claude plan or Console account

OpenAI Codex

Cloud and CLI coding agent available across ChatGPT, editor, and terminal.

Coding Agents & App BuildersPricing not verifiedBuild a website+1
Details & limits

Why it fits OpenAI Codex can work with an existing codebase to propose and review code changes for a reproducible problem.

PrepareAn accessible repository and reproduction steps

GetProposed code changes and an explanation

ReviewReview the diff and run your project tests

Keep in mindUsage and access depend on the connected account or API arrangement

Cline

Open-source coding agent for the IDE, terminal, and desktop.

Coding Agents & App BuildersFreeBuild a website+1
Details & limits

Why it fits Cline can work with an existing codebase to propose and review code changes for a reproducible problem.

PrepareAn accessible repository and reproduction steps

GetProposed code changes and an explanation

ReviewReview the diff and run your project tests

Keep in mindModel access needs setup through credits, provider keys or your own local compute.

Pi Agent

Open-source coding agent for terminal-based work with local files.

Coding Agents & App BuildersFreeFix a website+1
Details & limits

Why it fits Pi can read a local workspace, run commands and write files as part of a developer-controlled coding workflow.

PrepareA local codebase and reproducible error

GetCode changes or a diagnostic explanation

ReviewInspect the diff and run the relevant tests

Keep in mindNo Agenlify coding test is claimed here; the recorded Pi case is a separate CSV analysis task

Unstoppable

Run coding agents in parallel worktrees from one development workspace.

Coding Agents & App BuildersFree trialFix a website
Details & limits

Why it fits Unstoppable runs coding agents in parallel Git worktrees with review tools.

PrepareA repository and separate development tasks

GetAgent changes in isolated worktrees and reviewable pull requests

ReviewReview plans, diffs and CI before integrating changes

Keep in mindConnected agent subscriptions can add separate costs

AIRUNCODE

Local coding agents with your own model keys or local models.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits The official page describes filesystem changes, model configuration and test feedback in a local coding-agent runtime.

PrepareA local codebase, change request and configured model

GetCode changes, diffs and test feedback

ReviewReview diffs and rerun the relevant tests before shipping

Keep in mindThe free plan limits provider-key activation; multi-agent swarm is a Pro feature

Kiro

An agentic development environment that turns requirements into specifications and code changes.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits An agentic development environment that turns requirements into specifications and code changes.

PrepareA repository, reproduction steps and acceptance criteria

GetSpecifications and proposed code changes

ReviewReview the plan, diff and project test results

Keep in mindModel access varies by plan and region.

Google Antigravity

Google's agentic development platform spanning a desktop workspace, IDE and command line.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Google's agentic development platform spanning a desktop workspace, IDE and command line.

PrepareA codebase, bounded issue and test commands

GetProposed code changes and development artifacts

ReviewReview tool permissions, diffs and verification results

Keep in mindFree access has weekly rate limits.

OpenCode

Work on a code repository from a terminal, desktop app or IDE, with your choice of model.

Coding Agents & App BuildersFreeBuild a website+1
Details & limits

Why it fits Use OpenCode to investigate a reproducible issue in a repository, then review the proposed patch.

PrepareA code repository and a reproducible task

GetProposed repository edits and explanations

ReviewChoose the model and check its billing and data policy

Keep in mindReview model access, permissions and every code change; this is an official-source review, not an Agenlify hands-on test.

Gemini CLI

Use a Gemini-powered terminal agent with file, shell and web tools.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA project or task prompt and authorized Gemini access

GetFile changes, model responses and tool output

ReviewApprove shell access and verify code changes and external-source claims.

Keep in mindThe documented personal-account free tier has limits; other authentication paths may be billed.

Happy

Monitor and steer Claude Code or Codex sessions from a mobile or web client.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareAn authenticated coding CLI, a local project and a paired client

GetRemote session messages, approvals and underlying agent edits

ReviewVerify device pairing and review the underlying agent's commands and code diffs.

Keep in mindHappy is a wrapper; the coding agent and its model access must be configured separately.

Multica

Assign coding-agent work to issues and keep progress and review in a shared board.

Coding Agents & App BuildersPricing not verifiedFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareAn issue, a configured runtime and authenticated coding CLIs

GetIssue-linked run progress, agent comments and proposed code changes

ReviewReview the issue's run history and diff before approving its completion.

Keep in mindThe source-available license restricts third-party hosting and commercial embedding.

omp

Use a configurable terminal coding agent with language-server and debugger tools.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA repository, coding task and configured model provider

GetCode modifications, diagnostics and debugger or command results

ReviewReview tool permissions and code diffs and rerun the relevant tests.

Keep in mindThis Pi fork is a separate product; its MIT client still needs model access.

OpenHands

Operate coding agents across local, sandboxed or remote backends from Agent Canvas.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA repository, a task and an authorized agent backend

GetAgent conversation records and proposed repository changes

ReviewUse an isolated backend and inspect diffs and commands before approving changes.

Keep in mindThe documented no-sandbox option gives the agent full access to the host filesystem.

OpenWorker

Run a desktop AI coworker with governed tools and security-review workflows.

General AI AgentsFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareAn authorized repository or local task and configured model access

GetSecurity findings, proposed fixes and audited task results

ReviewValidate scanner findings, review remediation diffs and approve every consequential action.

Keep in mindSecurity findings still need expert review; the beta is not a security guarantee.

Orca

Run coding agents in separate Git worktrees and review their results together.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA Git repository, configured coding CLIs and a task prompt

GetIsolated agent worktrees, diffs and selected code changes

ReviewCompare candidate diffs and tests before merging a worktree into the main project.

Keep in mindOrca coordinates external agents; their subscriptions or model usage remain separate.

Paseo

Control existing coding agents across desktop, mobile, web and CLI clients.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareAn authenticated coding CLI, a local daemon and a paired client

GetRemote agent progress, approvals and underlying code changes

ReviewConfirm device authorization and review commands and diffs from the underlying agent.

Keep in mindTrusted plugins run with daemon access; the underlying agent is not bundled free.

SWE-agent

Let a configured language model use repository tools to propose issue fixes.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA reproducible repository issue, agent configuration and model access

GetA proposed patch and execution trajectory

ReviewReview the trajectory and diff and rerun the failing tests before accepting a patch.

Keep in mindMaintainers recommend mini-SWE-agent for new work; this listing is the original SWE-agent.

T3 Code

Control configured coding agents from desktop, mobile or web interfaces.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA supported authenticated coding agent and a local development project

GetAgent-session controls, approvals and underlying repository edits

ReviewCheck remote access and inspect commands and diffs before accepting agent work.

Keep in mindAt least one supported provider must be installed and authenticated separately.

Warp

Use a terminal-based environment with a built-in coding agent or external CLIs.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA repository, development task and configured agent access

GetTerminal output, code modifications and agent task results

ReviewReview shell execution and code changes and confirm cloud-service billing separately.

Keep in mindOpen-source client licenses do not establish free managed AI or factory-service access.

Zed

Edit code collaboratively and run configured agents from a native editor.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits Task links are limited to the documented workflow. Infrastructure and model components are not treated as ready-made end-user agents.

PrepareA project, development request and configured agent or model access

GetEditor changes, agent tool output and reviewable diffs

ReviewReview code changes and tool permissions and rerun relevant project tests.

Keep in mindThe open-source editor and hosted model access have separate licensing and billing boundaries.

Docker Agent

Define a debugging team in YAML and run it from your terminal with your chosen models.

Coding Agents & App BuildersFreeFix a website
Details & limits

Why it fits The stable documentation includes an investigator-and-fixer workflow for repository bugs.

PrepareA YAML agent configuration, a repository and a reproducible error

GetAgent responses, tool output and proposed code changes

ReviewChoose models, review their billing and set permitted tools before running.

Keep in mindConfiguring multiple agents does not guarantee better results or lower model spend; start with one reproducible issue.

Factory / Droid

Use Droid to plan, edit and validate repository changes from a desktop app or CLI.

Coding Agents & App BuildersPaidFix a website
Details & limits

Why it fits Use Droid to plan, edit and validate repository changes from a desktop app or CLI.

PrepareA repository, a reproducible issue and acceptance checks

GetProposed code changes, command output and validation results

ReviewReview every diff and rerun project checks before accepting changes.

Keep in mindSubscription tiers have different usage and access limits; they are not unlimited compute.