Agentic Systems

Agent Infrastructure

Scheduling, supervision, and memory for agents that run unattended

Role
Author
Year
2026
Status
Running continuously
4
agent CLIs unified
47
tests on the digester
Hourly
health monitoring
24 / 7
unattended operation

The problem

Agents that run on a schedule fail silently. The job stops, the log stops updating, and nobody notices for a week. Meanwhile the reasoning behind hundreds of decisions evaporates the moment each session ends.

What we built

Decisions That Mattered

1.

Digest the work

Four adapters read sessions from Claude Code, Codex, Grok, and opencode, classify each one to a project, summarize it through a cheap headless model, and file the result into a vault with per-project indexes.

2.

Break the feedback loop

The digester spawns model sessions, and those sessions land in the very stores it reads, which turned one backfill run into a self-feeding loop that doubled its own workload. A sentinel filter now excludes any session containing the digest instruction.

3.

Watch the watchers

An hourly monitor checks log freshness, process liveness, and an HTTP health endpoint across every always-on job, then notifies only when the failure set changes. An alert that fires every hour is an alert nobody reads.

4.

Compress the context

A local proxy, a knowledge-graph server, and a response-compression mode run across all four agent CLIs, so long sessions stay inside a context window and cost less to run.

What this demonstrates

Operating agents in production: scheduling, supervision, cost control, and institutional memory.

PythonlaunchdClaude CodeCodexGrokMCPObsidian

Get in touch

Start a Project

Tell us what you are trying to build and what is in the way. We will tell you early if we are not the right fit.

starrybodies@gmail.com