Swarm-based auto-research engine runs 500+ experiments on one agent thread
vincent_koc · x · 2026-11-02
AI engineer Vincent Koc shows a swarm-based auto-research engine he's building, running on harnesses like openclaw to experiment at speed and volume. After a few days it has executed 500+ experiments in a single agent thread, visualized as a large graph of results with explicit causal links and source references around a "Research result inventory" node — an early look at large-scale automated AI-scientist experimentation.
More from coding & agent
- From chat memory to knowledge graph: a two-layer wiki knowledge base pattern — adnan_hashmi · 2026-11-02
- Floorplan: open-source AI tool draws interactive maps of your codebase (2.1k stars) — adnan_hashmi · 2026-11-02
- GitHub Agentic Workflows hits GA: Markdown-defined automations, team velocity doubled with 91% AI commits — AIFlow_ML · 2026-11-02
- Building a knowledge graph from unstructured data using LLM extraction — adnan_hashmi · 2026-11-02
- LFM2.5-24B gets a Hermes agent LoRA: same accuracy with 20% fewer tool calls — yb2698 · 2026-11-02
- Using AI to write custom ComfyUI nodes that handle nested wildcards — Early-Ad-1140 · 2026-11-02