aws-samples

aws-samples / sample-autonomous-cloud-coding-agents

Public

Autonomous background coding agents on AWS. Turn tasks into pull requests via isolated runtimes, with built-in orchestration, observability, and governance.

aws-samples.github.iosample-autonomous-cloud-coding-agents agent-sandbox agentcore autonomous-agents aws code-sandbox
13
4
100% credibility
Found Apr 02, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Sample AWS platform for self-hosted AI agents that autonomously handle coding tasks on GitHub repositories by creating tested pull requests.

How It Works

1
🔍 Discover the magic

You find this helpful tool that lets AI agents fix code bugs and add features in your projects automatically.

2
🛠️ Set it up easily

Follow simple guides to connect it to your cloud account and prepare your code projects.

3
📂 Link your projects

Tell it which code repositories to watch, so it knows where to make changes.

4
✨ Send a coding request

Describe what you want fixed or added, like 'fix the login error', and let the AI get to work on its own.

5
📱 Watch the progress

Check updates anytime to see how the AI is doing with tests and changes.

🎉 Review and approve

Get a ready-to-merge update with all changes tested, and your project improves effortlessly.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 14 to 13 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is sample-autonomous-cloud-coding-agents?

This AWS CDK project deploys autonomous background coding agents that turn GitHub issues or task descriptions into pull requests. Submit via CLI, webhooks, or future Slack integration; agents clone repos in isolated MicroVMs, write code with Claude on Bedrock, run tests/lint via mise, and open PRs autonomously. Built in TypeScript with Python agents, it adds built-in orchestration, observability via CloudWatch, and governance like per-repo concurrency caps.

Why is it gaining traction?

Unlike real-time autonomous github copilot chats, this runs fire-and-forget in the cloud—ephemeral, measurable by PR outcomes, and self-improving via AgentCore Memory from past episodes. Developers get async automation without babysitting, plus repo-specific learnings like patterns from CLAUDE.md. Early hooks: CLI for submit/list/status, REST API, and webhooks for CI/CD pipelines.

Who should use this?

AWS teams automating routine fixes like "add tests to auth module" or "update README." Open-source maintainers offloading chores from GitHub issues, especially Python/JS/Node repos using mise. DevRel folks prototyping github autonomous coding agent flows before scaling.

Verdict

Experimental at 13 stars and 1.0% credibility—deploy via CDK, but expect iteration (roadmap eyes GitLab/Slack/multi-repo). Strong docs/site and test coverage make it worth a spin for AWS/Bedrock users chasing autonomous cloud coding agents.

(187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.