Jev ecosystem projects — page 66

Go SDK for TypeSafe AI API https://docs.typesafe.ai/api

Lints Jev requests before they are sent: offline checks for missing none-of-the-above options and broken state paths, then Jev itself for what structure cannot decide.

Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One.

Utilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions.

JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.

Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.

Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels

Typed System One layer for Rust (Choice/Score/Noul).

Unofficial typed async Rust client for the TypeSafe System One API

A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard.

Latency-first Rust SDK for TypeSafe System One.

Argus - a hedge fund in code. Autonomous quant research desk: 9 agents scan crypto markets 24/7, GPT-6 Astra writes candidate strategies, TypeSafe Jev routes signals and reviews code, and only strategies that clear strict out-of-sample gates are promoted. Paper trading only. Runs offline, no API key needed.

SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.

A desktop workspace for coding agents, parallel Git worktrees, and code review.

Set of agentic AI tools wrapped as an extension for the Pi harness.

Role-based subagent harness for pi (Lead/Planner/Developer/Tester lifecycle) with self-healing core patches, a live subagent-status widget, and a pluggable external-sink write gate.

OpenCode v2 plugin that sends permission requests resolved to "ask" to a model of your choice for review. Fails closed on every error, never overrides a configured deny, and writes every decision to an audit log.

A token efficient, local LLM friendly agentic coding harness: a complete agent runtime (agent loop, tool pipeline, sandboxing, session persistence) with four front-ends — a Blazor web UI, a headless CLI, and JSON-RPC / ACP stdio servers for editors and automation.

微信聊天内容记录搜索mcp

No project description available.

Workload-aware Pareto frontiers and dynamic model selection for agentic systems

Evidence-first career diagnosis and interview preparation plans.

Community plugins, developer tooling, and shared utilities for extending DeepSeek Harness — built as an Nx + pnpm monorepo.

A personal Claude Code harness: doctrine, mechanical gates, and curated skills. Holds no personal data by design.