Back to directory

AI DevOps Framework

An OpenCode plugin and framework for coordinating specialist AI agents, repository knowledge, safe Git workflows, and model routing across software, infrastructure, and business tasks, from intent through to a verified outcome.

AI DevOps Framework

aidevops is an OpenCode plugin and AI DevOps framework for carrying work from intent to a verified outcome. It combines specialist agents, durable repository knowledge, safe Git workflows, model routing, operational automation, and service integrations for software, infrastructure, business, marketing, content, research, and creative tasks.

Rather than treating each request as an isolated chat, it loads relevant context on demand, isolates work, gates consequential actions, retains evidence, and feeds lessons back into later work. It matches model capability and reasoning effort to the task, keeps secrets and protected data out of chat and Git history, and lets people and agents work in parallel without sharing unsafe mutable state.

It installs with npm and runs primarily on OpenCode, with Claude Code and Codex CLI supported as interactive runtimes. Routing is provider-neutral across simple, standard, and thinking workload tiers, and the core lifecycle runs from understanding through isolation, implementation, verification, PR, and an authority-aware merge or release.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.