Building veronica-core -- runtime cost and execution containment for LLM agent systems. Your agent retries 3 times per layer. Three layers deep, that's 64 API calls from one user click. veronica-core caps it.
veronica-core v3.4.2 -- Runtime containment for LLM agents
- Hard budget, step limits, retry caps, circuit breakers -- evaluated before the call reaches the model
- Semantic loop detection, MCP containment, declarative YAML policies
- AG2 integration merged (PR #2430), LangChain / CrewAI / LangGraph adapters
- 4844 tests, 94% coverage, zero required dependencies
pip install veronica-core
Construction consultant, 15 years. Regulated environments where failure has real cost. Now applying that mindset to LLM agent safety.
Python, C++, CUDA, TypeScript, WebGPU
Runtime containment, multi-agent orchestration, GPU kernels, 3D Gaussian Splatting
- The $0.64 bug: how nested retries silently multiply your LLM costs (dev.to)
- Zenn articles -- CUDA bugs, 3DGS, LLM agent cost control (Japanese)
Available for remote contract work -- AI safety, agent infrastructure, runtime systems.