# Honey I Shrunk The Kids

- **Event:** [Agentic Memory & Context Engineering Hackathon](https://cerebralvalley.ai/e/mongoDB-hackathon)
- **When:** Sat, Oct 11 at 9:00 AM – 10:00 PM (PDT)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Tal Globus](https://cerebralvalley.ai/u/tal), [Swapnil Surdi](https://cerebralvalley.ai/u/owlympic), [Aarya Harkare](https://cerebralvalley.ai/u/aarya_harkare), [Gowdhaman Sadhasivam](https://cerebralvalley.ai/u/gsadhas)
- **GitHub:** https://github.com/swapnilsurdi/histk
- **Demo video:** https://youtube.com/shorts/VXfbRdJAUGE
- **Gallery:** https://cerebralvalley.ai/e/mongoDB-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongoDB-hackathon/hackathon/gallery/66

Context is the ultimate bottleneck of LLM capabilities. We introduce a middleware for Langchain (and soon OpenCode and others) to dynamically assemble a complete context optimized for the task at hand with every message sent to the LLM.

Benchmarks (MT-RAG from IBM) show ~6% improvement in multi-step and multi-turn agent performance with a ~35% reduction in token count and cost and a ~22% reduction in latency compared to the current state of the art.

---

Markdown version of https://cerebralvalley.ai/e/mongoDB-hackathon/hackathon/gallery/66. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt