DeepSeek open-sources dsh-superagent, a multi-agent system built to minimize human attention
Arindam_1729 · x · 2026-11-11
DeepSeek open-sourced dsh-superagent, a multi-agent system that works through GitHub issues and PRs with multiple agents at once, designed around one claim: the bottleneck on multi-task coding agents isn't the model, it's your attention.
Key design choices:
- Long-lived router session: talks to humans and coordinates, never writes code
- Isolated workers: each accepted ticket gets a mandate and its own agent; follow-ups go straight to the owning worker
- Event-driven execution: new issues and mentions trigger work automatically
- Observe mode: unrequested work records a "would accept" and waits for you
The author notes an honest tradeoff in the design, acknowledging its limits.
Related event: DeepSeek Open-Sources Multi-Agent System dsh-superagent(2 posts)→
More from coding & agent
- Fable 5.2 takes over an existing Three.js/WebGPU hockey game to boost performance and add features — FinanceYF5 · 2026-11-11
- Your LLM fallback never fires for providers that stall before the first token — FallElectronic3774 · 2026-11-11
- MiniMax H3 image + Fable 5.2 turned into a 10-minute playable Three.js game — FinanceYF5 · 2026-11-11
- Fable 5.2 sparks a wave of one-prompt browser games: 10 community demos — FinanceYF5 · 2026-11-11
- Solo dev ships 5 updates a day with an agent loop: Sentry to auto-OTA fix — dshukertjr · 2026-11-11
- Vera: a Rust code indexing tool for AI agents combining BM25, embeddings and reranking — lemon07r · 2026-11-11