News for hackers. Stuff that matters.

loumaciel

It becomes the only MCP. All other MCPs are registered within the tool.
You can make MCP tools work for any type of data by using a proxy like https://github.com/lourencomaciel/sift-gateway/.

It saves the payloads into SQLite, maps them, and exposes tools for the model to run python against them. Works very well.

Re:Ask HN: What Are You Working On? (March 2026) on Monday March 09, 2026 @09:23AM (#47308747)
I’m building Sift, a drop-in gateway that makes LLM tool use far more reliable when tools return large JSON payloads. The usual pattern is that agents paste raw tool outputs directly into the prompt, which quickly blows up context, causes truncation/compaction, and leads to incorrect answers once earlier results disappear. Sift sits between the model and its tools (MCP, APIs, CLIs), stores the full payload locally as an artifact (indexed in SQLite), and returns only a compact schema plus an artifact_id. When the model needs something from the data, it runs a tiny Python query against the stored artifact instead of reasoning over thousands of tokens of JSON. In benchmarks across 103 questions on real datasets, this approach cut input tokens by ~95% and improved answer accuracy from ~33% to ~99%. Repo: https://github.com/lourencomaciel/sift-gateway.
Happy to answer questions about the sandboxing, artifact format, or the benchmark setup.

The benchmark harness and datasets are in the repo if anyone wants to reproduce or extend the tests. Curious if others have run into the same context compaction issues with tool-heavy agents.

Show HN: Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens

https://github.com/lourencomaciel/sift-gateway

LLM agents often place raw JSON tool outputs directly in the prompt. After a few tool calls, earlier results get compacted or truncated and answers become incorrect or inconsistent.I built Sift, a drop-in MCP gateway that stores tool outputs as local artifacts (filesystem blobs indexed in SQLite) and returns an `artifact_id` plus compact schema hints when responses are large or...

( Read More... | 1 comment | 6 points | on HN )
Re:US weighs Google break-up in landmark antitrust case on Wednesday October 09, 2024 @03:37PM (#41791792)
What alternative promotional strategies?
Re:US weighs Google break-up in landmark antitrust case on Wednesday October 09, 2024 @03:36PM (#41791787)
You don't rely on Google to handle everything, it's self-service. Whether you use Google or another platform depends entirely on where your audience is. For example, my father runs a small construction company, and 90% of his leads come from Google search. That’s where people are looking for services like his.
Re:US weighs Google break-up in landmark antitrust case on Wednesday October 09, 2024 @03:32PM (#41791759)
Online advertising has leveled the playing field, allowing smaller brands to compete with big names. Platforms like Google make it easy to capture attention, which is why even giants like Nike are losing market share to newer players. This shift spans all non-regulated industries. Without online ads, launching a nationwide brand would require enormous budgets, leaving us stuck with the same old monopolies.
Re:US weighs Google break-up in landmark antitrust case on Wednesday October 09, 2024 @03:03PM (#41791463)
Tons of small businesses rely on advertising. Tons of legit businesses only exist because online advertising became easy and widespread.
Re:Turning Everyday Gadgets into Bombs Is a Bad Idea on Thursday September 19, 2024 @07:01PM (#41597229)
In this analogy, what is water in the real world?
Re:Improvements to Data Analysis in ChatGPT on Thursday May 16, 2024 @07:14PM (#40384475)
https://www.findly.ai/ works with databases.
Re:Building ColdFusion for the Web on Sunday December 31, 2023 @07:36PM (#38828727)
Aha, I see, makes sense!
Re:Building ColdFusion for the Web on Sunday December 31, 2023 @10:06AM (#38824513)
Maybe they were expressing their confusion because you were speaking Spanish to people in Brazil?