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.
- Mission Control · hn · 2026-02-26 · 45 upvotes · similarity 0.58
- I am running 3 coding agents non-stop over the last 3 days. Here is how · hn · 2026-06-13 · 10 upvotes · similarity 0.54
- Computer Agents · hn · 2026-03-01 · 7 upvotes · similarity 0.51
- Lessons learned from running Claude Code swarms at scale · hn · 2026-06-05 · 10 upvotes · similarity 0.48
- Beehive · hn · 2026-02-24 · 47 upvotes · similarity 0.48
- Shikigami, run AI coding agents in parallel, each in a Git worktree · hn · 2026-07-19 · 7 upvotes · similarity 0.47
- Claude Code Routines · ph · 2026-04-15 · 599 upvotes · similarity 0.46
- I built an open-source alternative to Claude Cowork · hn · 2026-07-02 · 39 upvotes · similarity 0.46
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.