20+ Claude Code agents coordinating on real work (open source)
Details
- External ID
- 46990733
- Source
- HN
- Company
- —
- Product
- 20+ Claude Code agents coordinating on real work (open source)
- Website domain
- github.com
- Launched
- Feb. 12, 2026
- Cohort
- —
- Upvotes
- 53
- Upvotes percentile
- 0.8247978436657682
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
Single-agent LLMs suck at long-running complex tasks.We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress.How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agentsWe tested this on a Putnam-level math problem, but the pattern generalizes to things like refactors, app builds, and long research. It’s packaged as a Claude Code skill and designed to be small, readable, and modifiable.Use it, break it, tell me about what workloads we should try and run next!
Enrichment
- Theme
- AI agent frameworks and developer tools
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- multi-agent coordination system for software development
- Manually corrected
- False
Could you build this?
Yes Orchestrating multiple LLM CLI agents using a shared git repository, file locks, or basic coordination scripts is well within the capabilities of AI-assisted coding.
Discussion
20 comments analyzed.
Competitors mentioned: Claude Code, Beads, Open offline models, Primeageons 99 prompts
Concerns raised: Observation and monitoring overhead with multiple agents, Coordination complexity and orchestration costs at scale, Risk of agents baking in inefficiencies without complete business context, Context window limitations may not justify multi-agent complexity for most tasks, Human oversight becomes harder with more agents, reduces direct control
Feature requests: Better tooling for agent observation and introspection, Memory/context observability agent for understanding wide memory space, Clearer documentation on API key generation and recovery, Boilerplates for running on open offline models on VPS, Logging/output display for monitoring agent activity streams
Competitors
Other products that read as similar to this one — 900 launches clear the similarity bar, closest 8 shown.
Attention rank: #183 of 901 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 103 days after the earliest competitor.
- Mission Control · hn · 2026-02-26 · 45 upvotes · similarity 0.65
- OpenSwarm · hn · 2026-02-26 · 34 upvotes · similarity 0.59
- Agentic Orchestrator, a TUI for long-running coding agents · hn · 2026-06-30 · 20 upvotes · similarity 0.58
- 20x · hn · 2026-02-26 · 6 upvotes · similarity 0.57
- Lessons learned from running Claude Code swarms at scale · hn · 2026-06-05 · 10 upvotes · similarity 0.56
- I am running 3 coding agents non-stop over the last 3 days. Here is how · hn · 2026-06-13 · 10 upvotes · similarity 0.55
- Agent Flow: A beautiful way to visualize Claude Code actions · hn · 2026-03-26 · 5 upvotes · similarity 0.55
- Deep Work Plan · ph · 2026-09-14 · 6 upvotes · similarity 0.55
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.