Jev-assisted file retrieval and request caching for faster Pi workflows
Agent Tooling for Jev — page 5
882 repositories with documented relationships and source evidence.
Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.
TypeSafe Jev as the pi coding agent's quiet decision layer
80+ composable TypeScript recipes powered by Jev for AI agents, retrieval, answer verification, and conversation workflows.
使用 TypeSafe Jev 审查 Skill 与 MCP 可疑行为 | Review Agent Skills and MCP code with Jev, static evidence, and explicit coverage gaps
ALGAL is a new take on the agent graph: a language and runtime for agentic program evolution.
Typed decisions from the shell: an unofficial stdlib-Python CLI and Agent Skill for TypeSafe's Jev model, via the TypeSafe API (default) or OpenRouter. Yes/no, choice and ordinal scores with calibrated probabilities, semantic grep and batch mode.
Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js.
A minimal permission gate for Pi in the style of Claude Code's auto mode
Polymarket trading bot driven by Jev (TypeSafe AI) via OpenRouter
星露谷农场小助手:Jev 自主游玩、dsh 插件、独立 CLI 与 SMAPI Mod
Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning)
Skip expensive LLM calls when TypeSafe Jev says same intent. OpenAI-compatible local cache proxy — npx @kushalicious/jevcache
A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.
LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.
RuneBench harness for TypeSafe's Jev: bounded action catalog, tick-mode controller and a live dashboard
Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter
Pi extension suite powered by Jev: selective context compaction and model routing
Local Context Compiler (lcc): clean, dedupe and compact prompt context before it reaches the model, then report every block dropped, the cache tokens a pass invalidates and when pruning pays off. Runs offline with a local 1K decision model. MIT, no API key, zero telemetry.
Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your docs into each prompt, and check the final answer against the turn's own evidence.
An open-source, model-agnostic decision router for Claude Code and Codex.
Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.
DiffJury — TypeSafe Jev PR risk router + code review coach
Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.