We audit claims — we don't review tools.

Claude Code's capability claims largely hold as labeled, but its enforcement-language claims — deny rules, hook exit-code blocking, managed-policy precedence, shell-operator awareness, and per-provider model-alias resolution — are each contradicted by confirmed silent failures, several of which the vendor closed as stale rather than fixed.

A fast-moving, well-connected personal agent chassis whose headline self-improvement claim is not functional in any released version.

LangGraph's orchestration, streaming, and adoption claims hold as labeled, but its durable-execution and persistence label rests on a checkpoint layer whose documented enum and failure handling silently corrupts state — four serialization bugs, a double-interrupt snapshot bug, and a sync/async recovery divergence all re-verified open on 2026-07-17 against the 1.2.9 release line, the entire v1.0.10→1.2.9 span since Theory Delta first published them on 2026-03-29.

The unified-API and provider-breadth claims hold as labeled, but the production-control claims — budgets, rate limits, fallback, and the README's 8ms-P95-at-1k-RPS figure — are contradicted by issue-traced behavior under exactly the concurrent multi-tenant conditions the proxy is marketed for, with the key fixes unmerged and the backing issues stale-bot closed unfixed.

Ollama's simplicity, model-library, platform, and context-default documentation claims hold as labeled, but its tool-calling label is contradicted where it matters for agents — documented streaming tool support drops tool_calls chunks silently in production, and the get-running-in-minutes agent framing inherits a default context below the vendor's own agentic guidance on common hardware.