Official Vercel AI SDK evaluation provider. Choice, Score, and Boolean (Noul) over one state via experimental_evaluate.

ai-sdk.devadded sep 20

Official agent skill for designing System One workflows from Claude Code, Codex, and other skill-compatible agents.

github.comMITpushed sep 12165 forksadded sep 20

Official TypeScript / JavaScript client.

github.comTypeScriptMITpushed sep 1539 forksadded sep 20

Official synchronous and asynchronous Python client.

github.comPythonMITpushed oct 945 forksadded sep 20

Unofficial clients for Go, Rust, Ruby, PHP, .NET, Elixir, and Swift, tracked by language. All launched in Jev's first week — check the last commit before depending on one.

systemonemodels.orgadded sep 21

Native Swift 6 bridge that puts Jev behind Apple's Foundation Models framework interface.

github.comSwiftApache-2.0pushed oct 94 forksadded sep 26

Simon Willison's llm plugin for the OpenAI Decisions API: evaluate text and images with predicates, choices, and scores.

github.comPythonApache-2.0pushed oct 61 forksadded oct 12

Simon Willison's llm plugin for Jev and other TypeSafe models.

github.comPythonApache-2.0pushed sep 222 forksadded sep 23

TypeScript wrapper where every decision needs a required unsure branch — ignoring the uncertainty case is a compile error.

github.comTypeScriptMITpushed oct 11 forksadded sep 21

Vercel's open agent framework, where Jev powers the evaluate primitive and tool-approval policies.

github.comTypeScriptApache-2.0pushed oct 13613 forksadded sep 23

Semantic HTTP routing middleware for Hono: route requests by meaning, from Hono's creator.

github.comTypeScriptMITpushed sep 184 forksadded sep 26

MCP server of Jev judgment tools: verify, screen, find, rerank, classify, decide, compare, extract, review, and gate.

github.comJavaScriptMITpushed oct 1359 forksadded sep 20

Native MLX runtime for Laya on Apple Silicon: 7–14 ms decisions on an M3 Max, no GPU server needed.

github.comPythonApache-2.0pushed oct 10558 forksadded sep 22

Run Laya from Node.js / TypeScript via ONNX Runtime; the ~1.7 GB weights download from Hugging Face on first use.

github.comTypeScriptMITpushed sep 2176 forksadded oct 8

Provider-neutral System One runtime for TypeScript and Pi: write the choice / noul / score decision once behind a SystemOneProvider interface, run it on Jev, Reflex, or any compatible /v1/systemone endpoint.

github.comTypeScriptpushed oct 86 forksadded oct 13

Drop-in TypeSafeClient replacement backed by OpenAI or Anthropic, for comparing Jev against an LLM on the same questions.

github.comPythonMITpushed sep 2258 forksadded sep 20

MCP server as a single static Go binary, no Node or Python runtime. Sends usage guidance back to the client so the agent writes better questions.

github.comGoMITpushed oct 939 forksadded sep 23