Spencer Heckathorn

Keeping AI agents from losing the plot

About

I build open-source infrastructure for running real projects through AI agents. Creator of HyperWorker... a project management harness that stops drift, context loss, and unverified completion in long-running agent sessions.

Links

GitHub

Blog

X (Twitter)

Badges

Tastemaker

Veteran

Gone streaking

Forums

p/hyperworker

•

2d ago

What breaks when you run long projects through AI agents?

I've been using AI agents for multi-session projects (not one-shot tasks...actual work with phases, dependencies, and handoffs between sessions). Curious what patterns other people are seeing.

Some things that keep breaking for me:

•

22h ago

HyperWorker - Project management harness for AI agents

Your AI agent starts strong...then drifts, loses context, and skips steps. HyperWorker stops that. Six mechanisms in markdown and YAML keep long-running projects on track: Lock (no drift), Atomicity (no "mostly finished"), Dependency (no skipped steps), Memory (session survival), Precedence (rule conflicts), Verification (evidence-based completion). Point your agent at HARNESS.md and it scaffolds everything. Built in Cowork. Works with any LLM that reads files. Open source, MIT licensed.