Skip to content

Case studies ​

How Homer is run in practice: a real setup, the problem it solves, the configuration that does it, and what it leaves open. Each one is a pattern you can copy, not a feature of Homer; the reference documents stay the authority on what Homer itself does.

Workflows and people ​

Case studyIn short
A ticket-to-merge-request pipeline on LangGraphAn orchestrator whose state lasts days: fan-out to worker agents, human approval gates, and saving paid work when a step hits its turn cap.
Keeping long runs from losing workA per-ticket journal and work-in-progress snapshots, so a killed or re-triggered run continues instead of starting over.
Answering operator questions from chatA bridge over Homer's questions API mirrors every open question into chat, and reminders nudge only in working hours.
A review → fix loop that convergesAn arbiter, deterministic rails and a round cap that hands over to a human through ask-and-dispatch.
A factory that proposes its own fixesAn agent that reads run history and opens one merge request per proposed fix, without slowing the pipeline it studies.

Security and isolation ​

Case studyIn short
Runs that hold no credentialsA proxy beside each run adds the tokens, so a prompt-injected run has no token to leak.
A public chat intake for untrusted requestsAnyone may start runs from chat: per-thread locks, global caps, a path guard and a maintainer release gate.
Containing a Claude step: disallowedTools, not allowedToolsWith permissions skipped, allowedTools restricts nothing; disallowedTools keeps a step from spawning subagents.
LLM decisions that must carry proofA model may dismiss a security finding only with a verbatim quote that a script checks.
An agent as an MCP tool for another teamAnother team's agent calls one Homer agent over MCP, with a token that may run that agent and nothing else.

Capacity and scheduling ​

Case studyIn short
Runner pools on KubernetesA performance pool (2 runs at a time) for builds and a light pool (8 at a time) for everything else, picked by runnerTags.
One lock across several agentsmaxParallelRuns is per agent: a lock key shared by every agent that uses one build host.
One lane at a time, without parked runs blocking itOne pipeline computing at a time, where a run parked at a human gate does not hold the lane, and a watchdog for dead runs.
Warm caches for short runsCache roots on a volume and a cron agent that keeps them fresh: minutes saved per stage.
macOS build hosts for mobile buildsFrom an ssh runner behind a tunnel to self-registering pull-mode runners on macOS VMs.

Operations ​

Case studyIn short
Agent changes without downtime on KubernetesAgents on their own volume: an agent-only change swaps the files and calls the reload endpoint, with no pod restart.
Linting agent definitions in CIThe checks that catch, before merge, the agent mistakes Homer would only report at runtime.
Accurate cost through an LLM gatewayPricing runs from the gateway's real spend, which arrives late, plus cost by tag and cost limits.

Have a setup worth sharing? Open an issue describing it; see CONTRIBUTING.md.

Released under the Apache License 2.0. Documentation for 1.43.0.