Mubit + Neon: agent middleware cuts frontier-model tokens by 73%
JeremyCMorgan · x · 2026-11-20
Mubit is middleware for AI agents: a one-line endpoint change sits between your agent and the model, learns from every call, and moves recurring steps to small models tuned on your own traffic, keeping the frontier model for hard tasks.
A demo template on Neon Functions + Lakebase Postgres routes a data-analyst agent's calls through Neon AI Gateway. Results on the example workload: gpt-5.5 token usage down 73%, 40% faster, with no accuracy loss; lessons from verified runs help the agent avoid repeating mistakes.
Template: github.com/MubitLabs/mubit-neon-db-agent. The poster notes the methodology (repeated CL-bench runs, database branches) is worth inspecting before trusting the savings claim.
More from coding & agent
- Uber's Legal AI Agent Cuts Contract Review Time by 20% with 91% Accuracy Using RAG and Rules — nilukush · 2026-11-20
- Open-source MCP server gives your ChatGPT or Claude an A2A address so AIs can haggle with each other — IDforOpus · 2026-11-20
- The hardest work skill by 2028 won't be prompting — it's writing goals you can accept — evisoft · 2026-11-20
- Claude autonomously plays Taiko Web on a user's machine and hits a full combo — ezshine · 2026-11-20
- CTO Tracks PRs Per Engineer as AI Productivity Metric — PRs Doubled but Reverts Jumped to 23 — Few-Pilot7575 · 2026-11-20
- px0: A 20MB browser-based IDE for AI-generated code, built by chopping layers with first-principles thinking — arpit_bhayani · 2026-11-20