autonomous-loops

Autonomous Loops

Patterns, architectures, and reference implementations for running autonomous loops. Covers everything from simple sequential pipelines to full RFC-driven multi-agent DAG orchestration.

When to Use

• Setting up autonomous development workflows that run without human intervention
• Choosing the right loop architecture for your problem (simple vs complex)
• Building CI/CD-style continuous development pipelines
• Running parallel agents with merge coordination
• Implementing context persistence across loop iterations
• Adding quality gates and cleanup passes to autonomous workflows

Loop Pattern Spectrum

From simplest to most sophisticated:

Pattern	Complexity	Best For
Sequential Pipeline	Low	Daily dev steps, scripted workflows
Infinite Agentic Loop	Medium	Parallel content generation, spec-driven work
Continuous PR Loop	Medium	Multi-day iterative projects with CI gates
De-Sloppify Pattern	Add-on	Quality cleanup after any implementer step
RFC-Driven DAG	High	Large features, multi-unit parallel work with merge queue

---

1. Sequential Pipeline

The simplest loop. Break daily development into a sequence of non-interactive calls. Each call is a focused step with a clear prompt.

Core Insight

If you can't figure out a loop like this, it means you can't even drive the LLM to fix your code in interactive mode.

Chain calls to build a pipeline:

#!/bin/bash
# daily-dev.sh — Sequential pipeline for a feature branch

set -e

# Step 1: Implement the feature
opencode run "Read the spec in docs/auth-spec.md. Implement OAuth2 login in src/auth/. Write tests first (TDD)."

# Step 2: De-sloppify (cleanup pass)
opencode run "Review all files changed by the previous commit. Remove unnecessary type tests, overly defensive checks. Keep real business logic tests."

# Step 3: Verify
opencode run "Run the full build, lint, type check, and test suite. Fix any failures."

# Step 4: Commit
opencode run "Create a conventional commit for all staged changes."