Viewing profile — alexandroskyr

The benchmarks we ran can be found here: https://github.com/graph2agent/benchmarks

During the implementation of a huge high performance service. In order to keep context small (mainly for humans) I kept the specs into mermaid diagrams. When communicating with hum…

Leaving also here the GitHub repo: https://github.com/askahuman/askahuman

Problem Im solving: Im running 30+ fully autonomous agents. In some rare cases they get blocked because they cannot decide what direction to take. So I built a communication channe…

A zero-allocation Go decimal library with no big.Int fallback — 128-bit fixed-point arithmetic that benchstats ~35% faster than the fastest existing library, with exact alloc count…

Thank you a lot for the feedback. Yeah, still debating with my self regarding web-of-trust models vs KYC.

Agent interoperability protocols are starting to emerge (e.g. A2A / similar efforts), but I’m still unsure what the trust/identity layer should look like when agents need to contac…

Curious if anyone has seen differences in how models handle conflicting tool descriptions — e.g., two tools with overlapping capabilities where the boundary isn't clear. In my expe…

So mainly an mcp for facebook ads? Nice!