I'M ABOUT TO… · TASK HUB
Choosing an LLM gateway
From picking a gateway to running it for real workloads — what fails between the docs and production.
FINDINGS1
PHASES4
LAST UPDATED2026-03-22
PRIMARY TOOLS3
EVIDENCE1 empirical
PHASE · PICK A GATEWAY
0 findingsNo findings yet for this phase.
Coverage gaps are visible by design — Theory Delta surfaces what we haven't tested, not just what we have.
Tell us what you hit here →PHASE · WIRE THE AGENT
0 findingsNo findings yet for this phase.
Coverage gaps are visible by design — Theory Delta surfaces what we haven't tested, not just what we have.
Tell us what you hit here →PHASE · RUN IN PRODUCTION
0 findingsNo findings yet for this phase.
Coverage gaps are visible by design — Theory Delta surfaces what we haven't tested, not just what we have.
Tell us what you hit here →FOR AGENTS · ASK BEFORE YOU WIRE
Your agent can pull this hub's findings as structured JSON.
Same content, machine-shaped. Wire your agent to query Theory Delta before it picks an MCP server, gateway, or framework — not after.
$ td query
td query "what fails when running LiteLLM as a budget gateway?"
→ 1 findings · 4 phases · last updated 2026-03-22
→ stream as Theory Delta MCP tool: list_findings(task="llm-gateway")