SemIf
MIT local/WebGPU semantic conditionals — OpenJev, the former pitch name
AI Agents / Memory & Evals · OSS/MIT · 4.8k
Reviewed 2026-09-19 · last push 2026-09-23 · repo checked 2026-10-19
What's Good
MIT (TheoLeeCJ/SemIf). Runs semantic conditions against frozen open models locally, with a WebGPU path, and makes the decision from logits rather than asking the model to sample a response. OpenJev was the former/pitch name; the canonical repository is now SemIf. No closed inference endpoint required for the core experiment.
The Catch
Vs Instructor and structured JSON: SemIf is a logit-read semantic gate, not schema validation or guaranteed JSON. Vs closed TypeSafe Jev: the local/open-model route is the point, but you bring compatible weights, runtime, and calibration discipline — this is not calibrated RLCD. Youth note: ~1.6k★ in ~3 days clears the Panel bar, but the surface is still young.
Verdict
MIT local semantic conditionals. Read logits on frozen open models; do not confuse it with structured output or calibrated refusal.
Embed
Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.
Markdown
[](https://stackgems.com/gems/semif)
HTML
<a href="https://stackgems.com/gems/semif"><img src="https://stackgems.com/badge/semif.svg" alt="SemIf reviewed on Stack Gems" height="20"></a>
Related
AI Agents →- Mem0Memory infrastructure for AI agents that actually persists
- LangfuseOpen-source LLM observability you can self-host
- LettaEpisodic memory for agents that think across sessions
- PromptfooMIT LLM evals & red-teaming CLI; Community free, 10k probes/mo
- DeepEvalApache-2.0 pytest-style LLM/agent evals; Confident AI is the paid cloud