JevControl open-sources a tool to test if smaller models can run your agent's routine choices
airesearch12 · x · 2026-09-28
JevControl is a new open-source tool that answers whether smaller models can handle your AI agent's routine decisions (should I search again? which tool to use?). It imports agent traces from LangSmith, Langfuse, or OpenTelemetry, highlights decision points worth reviewing, and lets you compare the original setup against a test run with a smaller model. It never touches your production agent, and importing/reviewing traces requires no model calls. Commenters compare it to a DSPy GEPA-style optimizer over execution traces.
More from coding & agent
- Jev seen as fit for high-level robotics orchestration: fast schema beats LLM lag — ai · 2026-09-28
- Apple's free on-device fm paired with decision model Jev beats big-model routing in tests — jasonkneen · 2026-09-28
- Codex builds whole apps but keeps choking on reusing your live Chrome session — ChrisGPT · 2026-09-28
- DeepSeek ships Codex-style agent harness that connects to multiple model providers — ChrisUniverse · 2026-09-28
- Indie dev builds CoIsland, a notch-resident AI monitor with 37 connectors, entirely with Claude Code — DonTizi · 2026-09-28
- Andrew Carr says Astra gave bit-identical, hash-verified outputs on his weekend project — andrew_n_carr · 2026-09-28