Intent-based multi-model routing: autonomous agents manage Sparks-hosted Qwen, GLM, DeepSeek
jasonkneen · x · 2026-09-06
Developer Jason Kneen shares his evolving multi-model setup: two Sparks machines running MoE-style combinations of Qwen 3.8, GLM 5.3 and DeepSeek V4 Flash, swappable and usable in parallel.
With a custom proxy and playground, he no longer picks models — he picks an INTENT, and the system routes automatically using metrics, ratings and public data. Agents now run autonomously on the Sparks, maintaining, improving, optimizing, archiving and replacing services and models.
More from coding & agent
- Astra builds a polyphonic desktop app in just 9 hours — RileyRalmuto · 2026-09-06
- Local 27B + Pydantic AI writes the code that computes your real ledger — samuelcolvin · 2026-09-06
- Andreax Lists 157 AI Agent Tools with x402 Micropayments, No Signup — AncientLawfulness926 · 2026-09-06
- hostely: open-source Apple-native CLI self-hosts containers, Metal LLMs and HTTPS in one tool — ayo_ham · 2026-09-06
- Mollick: You Can't Really Turn Off Memory in Local AI Agents Like Fable and Astra — emollick · 2026-09-06
- PaperLens MCP Verifies Papers Are Actually Implemented in Code, Now Open Source — CraftyScore4348 · 2026-09-06