[L]

lazarevka research

We build agents that verify their own work. orca and coral are the first two.

build

the bet: capability lives in the harness, not the model.

orca

vuln research & verification agent, authorization-gated. a finding counts only once it reproduces in an ephemeral microVM — the environment issues the verdict, never the model.

rust · proprietary · api · v0.1 more

coral

a coding agent as one rust binary — every command runs inside a real os sandbox, the run stops at a budget in cents, and it answers to any openai-compatible endpoint.

rust · mit · repo coral more

research

where the products come from.

  1. machine intelligence reading what models do at inference time; measuring agents over long horizons ongoing
  2. cryptography & consensus consensus under realistic network assumptions, practical zk, mechanism design ongoing
  3. robotics closing the sim-to-real gap for embodied agents, measured on hardware ongoing
  4. computation verifiable compute, zk-vms, compute markets — proving and pricing computation ongoing

about

one of twenty villages, not a valley.

the research arm of lazarevka. we fund our own work and build when building teaches more than reading. orca is the first thing that survived.

part of
lazarevka
shape
distributed, small
funding
private means, no lps

contact

one inbox.

hello@lazarevka.xyz