Druids
Build your own software factory
Details
- External ID
- 47695666
- Source
- HN
- Company
- —
- Product
- Druids
- Website domain
- github.com
- Launched
- April 8, 2026
- Cohort
- —
- Upvotes
- 64
- Upvotes percentile
- 0.8618251928020566
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
Hi HN!Druids (https://github.com/fulcrumresearch/druids) is an open-source library for structuring and running multi-agent coding workflows. Druids makes it easy to do this by abstracting away all the VM infrastructure, agent provisioning, and communication. You can watch our demo video here (https://www.youtube.com/watch?v=EVJqW-tvSy4) to see what it looks like.At a high level:- Users can write Python programs that define what roles the agents take on and how they interact with each other.- A program is made of events - clear state transitions that the agents or clients can call to modify state. Each event gets exposed as an agent tool.- Druids provisions full VMs so that the agents can run continuously and communicate effectively.We made Druids because we were making lots of internal coding tools using agents and found it annoying to have to rearrange the wiring every time.As we were building Druids, we realized a lot of our internal tools were easier to express as an event-driven architecture – separating deterministic control flow from agent behavior – and this design also made it possible to have many agents work reliably.We had issues with scaling the number of concurrent agents within a run, so we decided to have each program run in an isolated sandbox program runtime, kind of the same way you run a Modal function. Each agent then calls the runtime with an agent token, which checks who can talk to who or send files across VMs, and then applies the tool call.Our early users have found the library useful for:- running many agents to do performance optimization- building custom automated software pipelines for eg code review, pentesting, large-scale migrations, etc...We've heard that the frontier labs have the infrastructure to quickly spin up 100 agents and have them coordinate with each other smoothly in various ways. We're hoping that Druids can be a starting point to make that infrastructure more accessible.
Enrichment
- Theme
- developer tools for AI agents
- Vertical
- Horizontal
- Function
- Workflow automation
- Audience
- B2B
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- software factory builder
- Manually corrected
- False
Could you build this?
Partial While multi-agent workflow DSLs can be vibe-coded, Druids provides managed VM infrastructure, sandboxed agent provisioning, and IPC at scale.
What it would actually take: Building this requires a backend cluster managing ephemeral microVMs (e.g., via Firecracker, Nomad, or Kubernetes with custom runtimes), secure sandbox isolation for untrusted generated code, and robust bidirectional streaming RPCs. Deep systems engineering and cloud infrastructure expertise are needed to handle multi-tenant isolation, instant VM snapshots, and cost-effective provisioning.
Discussion
15 comments analyzed.
Competitors mentioned: Cursor (with ACP support), Claude Code, Symphony (OpenAI factory)
Concerns raised: Sandbox-only environment limits local machine execution, Multi-agent coordination complexity at scale, Environment isolation reliability at scale, Code uses primitive obsession anti-pattern, Message protocol evolution causes drift
Feature requests: Cursor agent support, Local/non-sandboxed environment execution, Clearer state transition definition documentation, Agent trace visibility between agents, Standardized return address and messaging protocol
Competitors
Other products that read as similar to this one — 433 launches clear the similarity bar, closest 8 shown.
Attention rank: #63 of 434 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 156 days after the earliest competitor.
- Running AI agents across environments needs a proper solution · hn · 2026-03-24 · 8 upvotes · similarity 0.54
- Run coding agents in microVM sandboxes instead of your host machine · hn · 2026-04-23 · 63 upvotes · similarity 0.47
- Daemons · hn · 2026-04-21 · 70 upvotes · similarity 0.46
- Run AI coding agents in real, local sandboxes, not Git worktrees · hn · 2026-04-12 · 6 upvotes · similarity 0.45
- Mistle · hn · 2026-05-13 · 6 upvotes · similarity 0.45
- Sandbox Agent SDK · hn · 2026-01-28 · 41 upvotes · similarity 0.45
- I built an open-source Rust/TS AI agent runtime with a Next.js-style DX · hn · 2025-12-02 · 5 upvotes · similarity 0.45
- Burla · hn · 2026-08-14 · 6 upvotes · similarity 0.44
Other launches for this product
Same idea, different domain
Nobody's really built a workflow automation tool for Real estate yet.