Comparison

Several AI coding agents now run on GitHub. Pullfrog runs the same agent CLIs on your GitHub Actions runner and adds event triggers set in a console, tools built for CI, context that carries from run to run, and a sandboxed shell.

ProductFromWhere the agent runs
claude-code-actionAnthropicYour Actions runner
Codex on GitHubOpenAIOpenAI's cloud
run-gemini-cliGoogleYour Actions runner
OpenCode GitHub actionOpenCodeYour Actions runner
Copilot cloud agentGitHubAn ephemeral GitHub-hosted environment
PullfrogPullfrogYour Actions runner, GitHub-hosted or self-hosted

Pullfrog runs Claude Code for Anthropic models and OpenCode for every other provider, with an experimental Codex CLI harness for organizations that opt in (model resolution). Copilot also offers Claude and Codex as agents to Copilot Pro+ and Enterprise customers, in public preview since February 2026.

Models and credentials

Anthropic's claude-code-action runs Claude, Codex runs OpenAI models, Google's run-gemini-cli runs Gemini, and Copilot cloud agent picks from GitHub's model list. Pullfrog runs any major provider, and each account chooses how to pay:

  • Your own API key, including Amazon Bedrock, Google Vertex AI, Azure OpenAI, and OpenAI-compatible endpoints
  • A Claude, ChatGPT, Grok, or Kimi Code subscription you already pay for
  • Pullfrog Router, one prepaid balance across providers at provider cost with no markup
  • Free models, with no bill at all

Triggers

Each automation is a toggle in the repo console: a mention, a new PR, a push to a reviewed PR, a new issue, a review on a Pullfrog PR, a failing check. The vendor actions express the same events as workflow filters in YAML, which you write and maintain in each repository.

PR review

Pullfrog re-reviews a PR as new commits land, and closes out its own findings once they are fixed.

  • A re-review reads a git range-diff against the last reviewed commit, so its feedback covers only what changed.
  • Before it reviews, Pullfrog checks its own open findings, replies "Addressed in" with the commit, and resolves each thread the new commits fixed. Threads from human reviewers stay open for those reviewers.
  • The reviewer can hand open questions to read-only specialist subagents, several in parallel.
  • Fix all and Fix 👍s on a review turn its comments into a commit (addressing reviews).
  • With auto-merge on, an approval hands the PR to GitHub's native auto-merge, so branch protection still decides when it merges (auto-merge).

Tools built for CI

An agent in CI needs more than the GitHub API. Pullfrog ships its tools in the action, already authenticated:

ToolWhat the agent gets
CI logsAn index of the relevant lines from a failed check suite, a curated excerpt, and the full log on disk
PR checkoutThe PR branch checked out, fork pushes configured, and the diff written to a file
Dependency installDependencies install in the background while the agent reads code
File uploadA public URL for a screenshot or artifact, ready to embed in a comment
BrowserHeadless Chromium for checking a running app and taking screenshots
Progress commentOne comment, updated in place with the agent's task list
GitHubReviews with inline comments, replies, thread resolution, issues, PRs, and labels

Context between runs

Each review updates a PR-level snapshot that the next review of that PR reads first. Repo-level learnings collect durable facts about the codebase, and you can edit them in the repo console (learnings).

Hooks

Hooks run your scripts at fixed points in a run: once before the agent starts, after every branch checkout, and before a push. They run in the same sandbox and scrubbed environment as the agent's shell.

Shell and credential isolation

The agent has a real shell, git, and network access, but not your secrets. Its security layers:

  • Shell commands run in a Linux namespace sandbox. In Restricted mode, which is always on for public repositories and the default for private ones, a default-deny allowlist keeps secrets in the runner environment out of the shell.
  • Git authenticates with a one-time code per operation, so the GitHub token never enters the agent's environment.
  • Review and plan runs cannot push or commit code.
  • Pushes can be limited to feature branches, or turned off.
  • Mentions from non-collaborators are off by default. Every run a non-collaborator starts uses the Restricted shell and cannot push code.

By comparison, claude-code-action scrubs secrets from subprocesses and adds PID-namespace isolation only when it is set to accept triggers from users without write access (its security docs).

Cross-repository runs

With the --xrepo flag, one run can read and change several repositories in your organization (cross-repo runs). Copilot cloud agent works in one repository per task.

Pricing and license

The action is open source under the MIT license at pullfrog/pullfrog.

  • Personal accounts and public repositories run free.
  • Private repositories in an organization take one flat monthly plan per organization, with no per-seat charge.
  • Active open source projects can apply for funded models.

GitHub Copilot cloud agent

Copilot cloud agent is the closest alternative. It is built into github.com and supports MCP servers, hooks, custom agents, and automations that start sessions on events or a schedule.

Copilot cloud agentPullfrog
Where it runsAn ephemeral GitHub environment with restricted internet accessYour Actions runner, including self-hosted runners
ModelsGitHub's model listAny provider, with your key, a subscription, Pullfrog Router, or free models
PriceA Copilot plan, per granted seat on Business and Enterprise, plus one premium request per session times the model's rateA flat plan per organization for private repositories; models paid separately
Who can trigger itOnly users with write accessCollaborators; non-collaborators on the events you allow, without code pushes
Repositories per taskOneSeveral, with --xrepo
MemoryCopilot Memory, in public preview; entries expire after 28 days unusedPR snapshots and repo learnings you can edit
Built-in toolsGitHub and Playwright MCP servers; Playwright reaches only localhostGitHub tools, CI logs, uploads, a browser, and background dependency install

Copilot is ahead on reach and first-party integration:

Feature matrix

claude-code-actionCodex on GitHubrun-gemini-cliOpenCode actionCopilot cloud agentPullfrog
Runs onYour runnerOpenAI's cloudYour runnerYour runnerGitHub's cloudYour runner
ModelsClaudeOpenAIGeminiAny OpenCode providerGitHub's model listAny provider
Pays for models withAnthropic key or Claude subscription, Bedrock, Vertex AI, FoundryChatGPT planGemini API or Vertex AIYour provider keysCopilot premium requestsYour key, a subscription, Pullfrog Router, or free models
Triggers configured inWorkflow YAMLCodex settings and @codexWorkflow YAMLWorkflow YAMLGitHub UI and automationsRepo console
Automatic PR reviewWith a workflowYesYesWith a workflowWith Copilot code reviewYes
Context kept between runsNot documentedNot documentedNot documentedNot documentedCopilot Memory (preview)PR snapshots and repo learnings
Secrets scrubbed from the shellOnly when non-write users may triggerNot applicableNot documentedNot documentedNot documentedDefault-deny allowlist
Open sourceMITNo (cloud service)Apache-2.0MITNoMIT

When each option fits

  • A vendor action fits when you use one vendor's models, want an @mention or a review step, and are happy to own the workflow YAML for each event.
  • Copilot cloud agent fits when your team already pays for Copilot seats, starts work from IDEs, Slack, Jira, or Linear, and works in one repository per task.
  • Pullfrog fits when you want the agent to react to PRs, reviews, issues, and CI failures without YAML, to choose models and credentials per account, to carry context across runs, or to accept restricted runs from outside contributors. Start with getting started.
© 2026 Pullfrog, Inc.

On this page