I took inspiration from Cloudflares codemode where they took 2500 endpoints and turned them into consumable ~1000 token MCPs for agents to consume.
This basically takes your APIs, databases, and docs and compresses them into 2 MCP tools (~1,000 tokens) instead of N tools (100K+ tokens). Claude was burning tokens (and a lot of them for me) on just tool definitions. This compresses that considerably.
It's a typed SDK layer and not just a RAG for APIs. The search index holds function signatures instead of data.
We dogfood the Express, OpenAPI, and Database adapters daily. But the other adapters are implemented with tests but less mileage -- LAMBDAs is just an idea.
Would love to get feedback -- or even see if it's helpful for other people or if the recent expansion of context windows makes this irrelevant.
God help us all if our central bank starts taking cues from the Bank of Japan or the ECB and their zombie economies.
Our inability to suffer short-term consequences for long-term prosperity is a real issue that we as a country need to figure out how to solve. (Can you solve for human nature?) The fed shouldn't have made cuts in 2019 at the height of the market, we should have let failing banks fail, we need to start spending responsibly if we want to remain a reserve currency, and we need to learn that forest fires clear out the undergrowth for new growth.
While this may not be perfect composition, this is a surreal (and almost sad) moment in my life to hear music that is passable created by a computer under it's own volition. I work at a company that works with a lot of machine learning so I generally understand its limitations and haven't ever been an alarmist. That being said, I generally always thought of it being applied to automate work. For some reason I had always considered that which we normally attribute to human creativity to be off-limits. Sure now it's not great, but in 10 years will it be able to compose better music than Chopin? In 10 years, will music created by a computer surprise and delight me more than music composed by humans?
Pilot here - they used the example of a hurricane, however, I think it would have a daily impact on thousands of flights (general aviation and commercial) which all rely on on accurate weather forecasting. Weather is no joke in aviation; even if you're flying a 747.
This basically takes your APIs, databases, and docs and compresses them into 2 MCP tools (~1,000 tokens) instead of N tools (100K+ tokens). Claude was burning tokens (and a lot of them for me) on just tool definitions. This compresses that considerably.
It's a typed SDK layer and not just a RAG for APIs. The search index holds function signatures instead of data.
We dogfood the Express, OpenAPI, and Database adapters daily. But the other adapters are implemented with tests but less mileage -- LAMBDAs is just an idea.
Would love to get feedback -- or even see if it's helpful for other people or if the recent expansion of context windows makes this irrelevant.