Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Ductwork

A Go platform for running AI agents on autopilot

Details

External ID
47211499
Source
HN
Company
—
Product
Ductwork
Website domain
github.com
Launched
March 1, 2026
Cohort
—
Upvotes
5
Upvotes percentile
0.1070110701107011
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

I've been running Claude agents for various automation tasks — monitoring crypto news, syncing Todoist, running health checks — and I kept hitting the same problem: there's no clean way to deploy an agent that just runs on a schedule without a human babysitting it.Every agent framework I looked at was built around chat interfaces or one-shot workflows. I wanted something closer to cron for AI agents — define a task, give it a schedule, let it run forever. So I built Ductwork.You define tasks as simple JSON files — a prompt, a schedule, optional memory and skills — and ductwork handles scheduling, execution, retries, and history. The agents have bash, file read/write, and that's it. No fancy abstractions.The thing that makes it actually useful for unattended operation:Persistent memory — agents write to a memory directory between runs. My Bitcoin news monitor remembers which articles it's already reported on. Next run, it only flags new ones.Security boundaries — if you're letting agents run unsupervised, you need guardrails. Per-task tool whitelists, path restrictions, bash command filters. A monitoring task can't accidentally rm -rf something.Run history and observability — every run is tracked with status, duration, token usage, and errors. REST API for everything so you can integrate with whatever alerting you already use.It scales from a single process (ductwork start) to distributed — same binary with --mode=control runs a task queue, --mode=worker on other machines polls for work. No new dependencies, just HTTP.Single Go binary, go install and you're running. ~3,500 lines, only deps are the Anthropic SDK and Cobra.This is definitely not a finished product — it's early and there's a lot I want to add. But it's functional and I'd love for people to download it, play around with it, and let me know what they think. Feedback, ideas, issues — all welcome.https://github.com/dneil5648/ductwork

Enrichment

Theme
AI agent frameworks and developer tools
Vertical
Horizontal
Function
Agent / copilot
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
platform for running ai agents autonomously
Manually corrected
False

Could you build this?

Yes A Go daemon that runs scheduled jobs, monitors feeds, and triggers LLM agent tasks via API calls is a standard backend service suitable for vibe coding.

Discussion

4 comments analyzed.

Concerns raised: High API costs at scale with Anthropic, Limited task testing (only 4-5 concurrent tasks tested), No management/observability view yet, No agent-to-agent communication across task boundaries, Unclear scalability for many tasks/schedules

Feature requests: Management dashboard for viewing scheduled task dependencies, Session persistence and multi-agent observability, Checkpointing conversation state and filesystem for failure recovery, Inter-agent communication for cross-task scenarios

Competitors

Other products that read as similar to this one — 522 launches clear the similarity bar, closest 8 shown.

Attention rank: #490 of 523 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 118 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.