Launched March 4, 2025
Aviator Agents

Aviator Agents

An LLM framework for large scale code migrations

FreeAI Agents1,666 impressions#18 of its week

Introducing Aviator Agents - an LLM-based Agentic framework to perform large scale code migrations in your repositories. These agents emulate human patterns to perform migrations by finding references and documentation, understanding dependencies, breaking down large chunks of code, and verifying build status. Aviator Agents plan out steps to perform a task and iterate to improve accuracy. Unlike most LLM based frameworks, Aviator Agents is an end-to-end framework that connects directly with GitHub. This eliminates the need to set up a custom environment and build process. Aviator Agents integrates directly with GitHub and supports Open-AI o1, Claude Sonnet 3.5, Deepseek R1, and Llama 3.1 models. For early access, signup at: aviator.co/agents

A LLM-based framework that automates large-scale code migrations and PR workflows directly from GitHub.

for
Engineering teams that need automated code migrations, PR reviews and CI fixes.
pricing
freemium · free trial
license
MIT
aviator-co/av 509 48Goupdated a month ago
works withGitHubSlackChrome extensionJenkinsBuildkiteArgoCDSpinnaker

Key features

6 features of Aviator Agents
  • Spec-driven Runbooks — Generate detailed runbook specs for each task and execute them end-to-end.
  • One-click PRs from Slack — Turn a Slack message into a reviewable pull request with a single command.
  • Auto-scale Agent Infra — Ephemeral agent instances spin up on demand for each step.
  • CI Failure Detection — Agents parse build logs, identify root causes and submit automated fixes.
  • Automated Issue Triage — AI triages issues, asks clarifying questions and creates draft PRs.
  • Verification Runs — Up to 10 PR verification runs per month in the free tier to ensure intent matches code.

Use cases

  • Migrate a monorepo from Node.js 14 to 18 across dozens of services
  • Automate PR creation and review directly from Slack messages
  • Detect and fix flaky CI tests and dependency conflicts automatically
  • Triaging incoming GitHub issues and turning them into executable runbooks
  • Refactor large codebases to improve readability and build times

Aviator Agents pricing

  • Free$0Personal & team inbox · Stacked PRs CLI · Chrome extension · 10 verification runs/month
  • Team$20/dev/mo/monthEverything in Free · Smart routing & SLOs · Parallel MergeQueue with flaky test handling · Up to 10 repositories
  • Scale$50/dev/mo/monthEverything in Team · Monorepo-aware MergeQueue · Advanced ownership & cross-team routing · 50 verification runs per user/month

Aviator Agents vs alternatives

Aviator AgentsFineSuperAGI CloudCalljmpReviewPhin
Best forLLM-driven code migrations with GitHub integrationGeneral AI-agent software developmentCloud-hosted autonomous AI agentsManaged AI-agent backendSelf-hosted AI code review
PricingFreemiumFreeFreeFreeFree
DevHunt upvotes075433512
LaunchedMar 2025Jan 2023Jan 2023Feb 2026Jul 2026

Aviator Agents FAQ

Can I get a custom package?+

Yes – Enterprise customers can request custom contracts and limits by contacting sales.

Does the 14-day Team trial require a credit card?+

The documentation mentions a 14-day free trial for the Team plan but does not specify a credit-card requirement.

What is a Verification run?+

A Verification run checks a pull request against the intended spec, ensuring the generated code matches the original intent.

Can I bring my own AI keys?+

Enterprise plans allow you to use your own OpenAI, Claude, or Bedrock keys with no credit limits.

Summarized by DevHunt from aviator.co · Sep 27, 2026. Details may change; check the official site.