A TypeScript toolkit of production patterns around the Jev SDK: decision contracts, confidence-threshold routing with fallback and review paths, an offline evaluation harness, and a RAG diagnosis showcase.
Read from GitHub on . Counts change daily.
const result =
sdkOptions === undefined
? await this.client.systemOne(sdkRequest)
: await this.client.systemOne(sdkRequest, sdkOptions);
validateSystemOneResult(request.questions, result);
const usage = result.usage;View in src/providers/jev-provider.ts
Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. The public deployment runs in dry-run mode with a mock model.
jarrodwattsOpenjev-trader on github.com2.2k starsLoop, mock model p50 100 msDecision window ~300 ms/block
MCP server that gives Claude Code, Codex, Amp, OpenCode and other agents ten Jev judgment tools, each returning typed probabilities they can branch on. The author calls it early software.
320 starsPer call 150-500 ms
Modernized BERT encoder used as the backbone for fast fine-tuned classifiers and rerankers. The non-generative baseline Jev's cost and latency claims are usually measured against. Star count is GitHub's rounded display figure.
Agent skills for Hermes, Claude Code and Codex that hand Jev the routing decisions: which model tier to use, which search results to open, which memory passages to read and which hide injected instructions. Ships a dashboard with an on, shadow and off switch and publishes measured latencies per skill.
Python library from Nokia researchers that reads typed Choice, Noul and Score answers with probabilities from an open LLM's logits or hidden states, without fine-tuning. Its zero-label level reduces option-order bias, and a head fit on 100 to 300 labels can run behind vLLM.
Places Jev as a fast supervisor above slower Codex coding agents. Codex workers do the engineering while Foreman independently assesses whether the work is complete, requirements are met, tests suffice, or human input is needed.
