// PROOF SURFACE

Every claim.
Sourced.

One page. Five sections. Every Melaya headline number next to its source. Click into a section to see the per-item enumeration, the reproducible bench command, or the raw JSON-LD.

LIVE · PROOF SURFACE

Six claims. Six sources.

TOOLS / CATALOG
1,912
public tool functions

Every async def agent-callable function enumerated at build time from the canonical Python source.

View full catalog
SUBAGENTS / CREWS
111
persona templates

ReAct agent definitions across all crew folders, generated from the platform crew definitions.

View all personas
AI PROVIDERS
23
model providers

Cloud, local, and open-router providers. Add one entry, the picker and codegen pick it up.

View providers
ENGINE / P50
310 ns
state_ticker write · p50

Rust engine, in-process monotonic clock. 89,033 samples, engine 0.4.48. Full pipeline p50: 14.4 µs.

Full latency matrix
FRAMEWORK / METRICS
16
metrics measured

Python agentic runner: tool dispatch, RAG retrieval, model-call overhead, HITL gate, pipeline orchestration.

Full framework bench
METHODOLOGY / OSS
Open
reproducible · Apache 2.0

Everything on this page is reproducible from a fresh clone. Bench harnesses in the public OSS repo.

OSS repo
Join the community
// Cookies
Melaya uses a small set of first-party cookies that are strictly necessary to authenticate you, maintain your session, and protect the platform from abuse. We do not use advertising cookies, cross-site trackers, or third-party analytics by default. The full cookie list is in our Privacy Policy.