neckbeard is a DevOps/platform plugin for coding agents that turns an application repository into reviewable cloud infrastructure with a cost estimate attached.
Follow neckbeard to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.
The agent analyzes the repo and asks the questions code can't answer, then a deterministic Go CLI maps the answers onto a human-maintained, CI-tested catalog of OpenTofu modules, so the agent never invents infrastructure.
- 01
`/neckbeard:analyze` builds an app profile where every fact cites a file and line, inferences carry confidence and open assumptions block planning
- 02
`/neckbeard:estimate` prices the plan against the catalog with Infracost before anything is created
- 03
`/neckbeard:sync` scaffolds OpenTofu, CI pipelines and Kubernetes manifests, validates them and reports what was and wasn't proven
- 04
Hash-verified blueprint.yaml and a pure-function renderer that refuses to overwrite hand-edited files
- 05
Covers AWS, GCP and Azure as serverless containers (Cloud Run, ECS Fargate, Container Apps) or Kubernetes (EKS, GKE, AKS) with GitHub Actions or GitLab CI
- 06
Installs as a Claude Code plugin marketplace entry; SKILL.md install for Codex, Cursor and other hosts; budget alerts and cost ceilings per environment
Free
Free and open source under Apache-2.0 with no account. You pay only for your coding agent's model usage and for the cloud resources you choose to deploy; optional helpers such as Infracost, OpenTofu and Checkov are separate tools.
Best for
Teams using Claude Code, Codex or Cursor who want agent-assisted infrastructure that stays within a vetted module catalog, with a reviewable diff and a monthly cost estimate before deploying.
Not ideal for
Apps needing services outside the catalog's single workload shape (for example Redis today), or teams wanting a fully managed PaaS rather than reviewing generated OpenTofu and pipelines.
A thoughtful guardrail-first take on agent-driven infrastructure: deterministic rendering from a tested catalog plus upfront cost estimates addresses the main failure modes of letting agents write IaC, though catalog coverage is still narrow.
v0.3.0 (October 15, 2026) added real per-environment budget alerts with a refusing cost ceiling, mapped Docker Compose images to datastore capabilities and documented running alongside ponytail; it was discussed on Hacker News on October 14, 2026.
As of
Is neckbeard free?+
Yes - neckbeard is Free. Free and open source under Apache-2.0 with no account. You pay only for your coding agent's model usage and for the cloud resources you choose to deploy; optional helpers such as Infracost, OpenTofu and Checkov are separate tools.
Is neckbeard open source?+
neckbeard is not listed as open source on ai.dosa.dev - it is Free.
Who is neckbeard best for?+
Teams using Claude Code, Codex or Cursor who want agent-assisted infrastructure that stays within a vetted module catalog, with a reviewable diff and a monthly cost estimate before deploying.
Who is neckbeard not ideal for?+
Apps needing services outside the catalog's single workload shape (for example Redis today), or teams wanting a fully managed PaaS rather than reviewing generated OpenTofu and pipelines.
What are the best neckbeard alternatives?+
The closest neckbeard alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.
Who makes neckbeard?+
neckbeard is developed by bealesh. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.