# Forge

- **Event:** [The Harness Engineering & Model Wrangling Hackathon](https://cerebralvalley.ai/e/mongodb-nyc-hackathon)
- **When:** Sat, Sep 26 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Team:** [Adish Padalia](https://cerebralvalley.ai/u/Adish26), [Dharm Patel](https://cerebralvalley.ai/u/dharmpatel02), [Neel Barve](https://cerebralvalley.ai/u/supiktalka)
- **GitHub:** https://github.com/DharmPatel02/toolsmith
- **Demo video:** https://www.youtube.com/watch?v=lGv79t3B_9A
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/72

ToolSmith is a procedural memory layer for AI agents that turns repeated work into tested, reusable tools. It watches how people and agents work, both on screen through a Chrome extension and a frame interpreter and in structured logs, and spots the workflows they repeat week after week. It only proposes a tool when a workflow truly recurs, and it visibly declines one-off binges and inconsistent routines. For each accepted pattern it writes the specification, code, tests and a plain-language tutorial. The tool must reproduce the user's real past results in a network-isolated sandbox before anyone can approve it. Once in use, a tool earns autonomy step by step, from dry-run to supervised to autonomous, and is demoted instantly on failure. When a site's layout changes and a tool breaks, ToolSmith detects the drift, diagnoses the change, and releases a fixed version that passes on both the old and new page. It also tunes its own guardrails: stricter settings apply automatically, while looser ones wait for the user's approval. MongoDB Atlas runs the whole system:
- Hybrid vector search ($rankFusion) and multimodal embeddings recall past work and match screenshots.
- $graphLookup resolves tools built from other tools.
- Change streams drive the background workers.
- Multi-document transactions make promoting a tool all-or-nothing.

The result: a repeated nine-minute, 18,000-token task becomes a verified tool that runs in seconds.

## More from The Harness Engineering & Model Wrangling Hackathon

- [Morgadarsha](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/69)
- [Robologue](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/70)
- [Visai](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/71)
- [Immune-Harness](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/73)
- [Proofread](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/74)
- [Omega](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/75)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/72. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt