jevQL: Semantic SQL for Postgres
jevql is a CLI/SDK that adds Jev semantic predicates, choices, and scores to ordinary Postgres SQL. It calls TypeSafe AI's System One model via the Jev API and supports Go, TypeScript, Python, MCP, and HTTP.
OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
jevql is a CLI/SDK that adds Jev semantic predicates, choices, and scores to ordinary Postgres SQL. It calls TypeSafe AI's System One model via the Jev API and supports Go, TypeScript, Python, MCP, and HTTP.
Gut is an Elixir library that maps subjective input to a fixed value and supports configuring the TypeSafe Jev evaluation model.
A lightweight script that adapts vLLM services to a Jev-style interface, enabling Choice, Score, and Noul decisions via logprobs.
An n8n community node that classifies, scores, and checks text with TypeSafe AI's Jev/System One model, supporting parallel requests and multi-item batching.
A skill that uses TypeSafe's Jev (System One) model to reduce context token usage in coding agents, with A/B test evidence and cost/latency measurements.
A Jev-powered skill router and security auditor for AI agents, using TypeSafe Jev System One for skill selection and prompt injection/dangerous command scanning.
JevRE is a Python CLI integrating TypeSafe AI's Jev System One model to recommend the next investigation step in Android reverse engineering. It includes a real Jev API client and an offline mock mode.
A read-only trading journal and review harness integrating TypeSafe AI's Jev for typed judgments, with a finance-jev-v1 benchmark and agent integration; it does not execute trades.
EdgeJev is a local and offline Jev / System One inference tool that supports multiple open-source reimplementations, running on CPU via ONNX and INT8 quantization without torch.
Jev Browser integrates TypeSafe AI's Jev/System One decisions with Playwright for browser automation, offering SDK, CLI, and MCP server with native operations and semantic assertions.
A playable stealth game using TypeSafe AI's Jev for guards' split-second judgments, with deterministic code owning the world. Includes live-run evidence and a Decision Lens for inspecting typed decisions.
Uses TypeSafe AI's Jev (System One) model to drive the ego lite browser: one indexed element table in, one operation and target out per request. Includes comparative benchmarks showing ~2x faster than per-step LLM loops.