Open Source
-
Cactus Whistle: 17 MB Speech-to-Text, Tested in French
I ran Cactus Whistle, a 16.9 MB open speech-to-text model, on Québec French, accented English and noise. Here is what it got wrong.
-
MXC Sandbox: Where Your Agent’s Code Should Run
I tried to install the MXC sandbox v1.0.0 on Linux and it failed on node-pty. Here is what it takes to run LLM-written code at a small startup.
-
WebMCP: I Tested Chrome’s Tool API for Browser Agents
WebMCP lets a web page hand tools to a browser agent. I ran it in Chromium 153, hit one real bug, and sketched a half-day Trellis experiment.
-
Codebase Port Cost: What ts-rust Really Took
ts-rust ported the TypeScript compiler to Rust with agents. I ran it and read its own numbers: the codebase port cost $24k after a $400k stall.
-
LiteLLM Budget Limits: max_budget Needs Postgres
A LiteLLM budget cap does nothing without a database. I tested v1.104.0, then set up per-agent keys and a team spend limit in ten minutes.
-
Vectorless RAG: Reasoning Over a Tree, Not Cosine Search
Vectorless RAG swaps embeddings for a table-of-contents tree the LLM walks. What PageIndex does well, what a query costs, and who should skip it.
-
MoE Expert Offloading: 125B on a 12GB GPU, With Catches
MoE expert offloading lets a 12GB GPU run a 125B model, but only for one user at a time. What Strata's numbers say, and what I'd run instead.
-
Open-weight decision models: Clef vs Strands Decider
Clef and Strands Decider 2B are open-weight decision models that return a calibrated score, not text. Here's what shipped and why it matters.