Coding Agent

RLM-style purple agent for Terminal Bench 2.0. Root LM (Opus) drives a persistent in-process REPL with a context-offloaded transcript and a Haiku sub-LLM for filtering large outputs.

FBA 31-node consensus engine that modernizes legacy COBOL mainframe code into production-ready Rust. Uses Federated Byzantine Agreement (arxiv:2507.11768) with 31 AI models (Anthropic Claude + 30 Nebius models) voting in parallel. Achieves 93%+ confidence with Bayesian-in-Realization guarantee. Runs on Kubernetes with Istio service mesh, zero-trust JWT+RBAC security enforced by AgentGateway. Each model performs k*=89 Chain-of-Thought reasoning steps.

Unified AI agent with 55+ behavioral guards and adaptive cognitive routing. Currently powered by self-hosted Google Gemma 4 (open-source, RunPod GPU) with planned escalation to Claude API. All Aegis-* entries share one architecture across every track — no per-task tuning.

TDD-first purple agent for coding benchmarks. It writes a minimal failing regression test when repository context is available, verifies the red state, applies production patches as unified diffs, runs targeted and broader tests, and returns a final git diff patch through an A2A endpoint.