ABCA (Autonomous Background Coding Agents on AWS) is a sample of what a self-hosted background coding agents platform might look like on AWS. Users can create background coding agents, then submit coding tasks to them and the agents work autonomously in the cloud — cloning repos, writing code, running tests, and opening pull requests for review. No human interaction during execution.
The platform is built on AWS CDK with a modular architecture: an input gateway normalizes requests from any channel, a durable orchestrator executes each task according to a blueprint, and isolated compute environments run each agent. Agents learn from past interactions through a tiered memory system backed by AgentCore Memory, and a review feedback loop captures PR review comments to improve future runs.
Users submit tasks through webhooks, CLI, or Slack. For each task, the orchestrator executes the blueprint: an isolated environment is provisioned, an agent clones the target GitHub repository, creates a branch, works on the task, and opens a pull request.
Key characteristics:
- Ephemeral environments — each task starts fresh, no in-process state carries over
- Asynchronous — no real-time conversation during execution
- Repository-scoped — each task targets a specific repo
- Outcome-measurable — the PR is either merged, revised, or rejected
- Fire and forget — submit, forget, review the outcome
- Learns over time — the more you use it, the more it self-improves
Each task follows a blueprint — a hybrid workflow that mixes deterministic steps (no LLM, predictable, cheap) with agentic steps (LLM-driven, flexible, expensive):
- Admission — the orchestrator validates the request, checks concurrency limits, and queues the task if needed.
- Context hydration — the platform gathers context: task description, GitHub issue body, repo-intrinsic knowledge (CLAUDE.md, README), and memory from past tasks on the same repo.
- Agent execution — the agent runs in an isolated MicroVM: clones the repo, creates a branch, edits code, commits, runs tests and lint. The orchestrator polls for completion without blocking compute.
- Finalization — the orchestrator infers the result (PR created or not), runs optional validation (lint, tests), extracts learnings into memory, and updates task status.
For the full architecture, see ARCHITECTURE.md.
ABCA is under active development. The platform ships iteratively — each iteration adds features and builds on the previous one.
| Iteration | Status | What it delivers |
|---|---|---|
| 1 | Done | Agent runs on AWS, CLI submit, branch + PR |
| 2 | Done | Production orchestrator, API contract, task management, observability, security, webhooks |
| 3a | Done | Repo onboarding, per-repo GitHub App credentials, turn caps, prompt guide |
| 3b | Done | Memory Tier 1, insights, agent self-feedback, prompt versioning, commit attribution |
| 3bis | Done | Hardening — reconciler error tracking, error serialization, test coverage gaps |
| 3c | WIP | Deterministic validation, PR review task type, multi-modal input |
| 3d | Planned | Review feedback loop, PR outcome tracking, evaluation pipeline |
| 4 | Planned | GitLab, visual proof, Slack, control panel, WebSocket streaming |
| 5 | Planned | Pre-warming, multi-user/team, cost management, guardrails, alternate runtime |
| 6 | Planned | Skills learning, multi-repo, iterative feedback, multiplayer, CDK constructs |
See the full ROADMAP for details on each iteration.
Follow the Developer Guide to set up your environment and deploy the application to your AWS account. Then, follow the User Guide to learn how to use the system.
A documentation site is available containing all design documents, roadmap and guides to deploy and use the platform. You can access it here.
The example provided in this repository is for experimental and educational purposes only. It demonstrates concepts and techniques but are not intended for direct use in production environments.
This library is licensed under the MIT-0 License. See the LICENSE file.