OpenCode Agent Router is a plugin for OpenCode v2 that dynamically routes subagent tasks to different configured models by querying Jev for structured model selection before creating child sessions. The plugin supports multiple models, skips rerouting resumed sessions, and omits sensitive data from routing requests.
A delivery app engineer discovered that their Redis caching layer for route estimates was inefficiently distributing keys across hash slots, causing MGET operations to be split into individual requests. By learning how Redis hash slots work and restructuring their key format, they were able to optimize the batching of multi-key commands to improve latency.
A BGP hijack attack on hosting software vendor Softaculous Ltd used a forged BGP route and valid TLS certificates to deliver malicious updates to a small number of installations. The attacker hijacked IP space 162.55.80.0/24 through NexonHost, exploiting RPKI validation gaps to propagate the route globally before legitimate routes countered it.
PlusWeb is an open-source Express-style HTTP server framework written in C++17 using libuv and llhttp. It handles routing through a segment trie and demonstrates significantly better performance than Express, maintaining consistent throughput even with thousands of routes while using substantially less memory.
CaptainCode is a unified agent coordinator that routes tasks across multiple AI models (Claude, Codex, Cursor, Grok) and APIs based on complexity and cost. Users can control model selection through commands like /frontier for demanding work, /cheap for cost efficiency, and /team for multi-agent synthesis, while maintaining a single conversation interface across their existing subscriptions.
Jev is TypeSafe AI's model for making typed decisions on text or JSON data, useful for routing, ranking, and agent actions. This page curates 33 reviewed Jev demos, tools, skills, and integrations from X, GitHub, and YouTube, with SDKs for Python and JavaScript, browser utilities, and local alternatives.
Relay is a self-hosted LLM gateway that routes requests across multiple AI providers (OpenAI, Anthropic, Bedrock, Groq, etc.) through a single API. It offers smart routing, request pacing, fallback management, and usage tracking in a single Go binary with an integrated dashboard, designed for AI agents and applications.
Jev-router is a CLI tool that automatically routes tasks between fast and strong Claude and OpenAI models based on complexity, preserving each CLI's native interface and authentication. It requires Node.js 20.12+, a TypeSafe API key, and can be installed globally via npm or run locally.
System One models like Jev are fast, efficient classifiers designed for routing and categorization tasks. They take a state and typed question, returning JSON with probabilities for each predefined answer option. Built by TypeSafe AI using RLCD training to ensure trustworthy confidence scores, they're 6-7x cheaper than large language models for high-volume classification but limited to fixed-set answers.
TypeSafe AI's Jev model returns typed decisions and probabilities for application workflows. It can route forms, prioritize tickets, review tool calls, categorize documents, and flag content by interpreting context and evidence. Applications should use Jev for interpretation-based decisions while keeping fixed business rules in code.
Jev, a non-generative decision model, generated 36M views in two days, prompting six open-source clones including ModernBert and Diffusion variants within 48 hours. The model is positioned as a fast 'System 1' complement to LLMs for routing, calibrated probability tasks, and browser-based workflows, though debate centers on speed versus quality and the lack of standard benchmarks.
Transom is a native macOS application that manages multiple browser profiles by grouping windows into profile-oriented stacks with a glass tab strip overlay. It supports ten browsers including Chrome, Firefox, and Arc, and automatically routes web links to selected profiles based on customizable rules. The tool requires macOS 13+ on Apple silicon Macs and operates as a menu-bar accessory without a Dock icon.
A visual documentation of Internet growth from 1997 to 2021, tracking network topology through routing table data and BGP information. The project visualizes how dominant network names evolved through mergers and acquisitions, with detailed maps created in 2003 and 2010 using different data sources and color schemes based on IP space allocation.
Jev is TypeSafe AI's decision-making model that answers typed questions in parallel within milliseconds, returning calibrated probabilities instead of generating text. JevMade is a community registry showcasing 743 verified experiments built with Jev across games, agents, routing, and automation tasks.
Expanso and Jev demonstrate a hybrid log-processing system combining deterministic rules with AI judgment. A severity-only baseline routes logs by level alone, while the pipeline adds contextual analysis—occurrence counts, time windows, and model scoring—to improve routing decisions. The system remains inspectable by showing baseline versus model-assisted decisions side-by-side.
Jev integration with DeepClause and Pi enables probabilistic logic programming for routing and decision-making tasks. The system combines LLM capabilities with Prolog-based determinism to handle customer message triage efficiently, using structured predicates for safety checks, classification, and routing decisions.
Vercel Labs released Jev AI SDK Template, a Node.js form router that uses AI models to intelligently route submissions by context. It combines Jev for primary evaluation with OpenAI's gpt-5.6-luna-fast as a fallback, includes optional email delivery via Resend, and requires Vercel AI Gateway access for deployment.
Find-jevable-code is an agent skill for Claude Code and Codex that audits repositories to identify semantic decisions (routing, triage, relevance, escalation) that could be converted into Jev primitives: Choice, Score, or Noul. The read-only pipeline surfaces opportunities ranked by code evidence without invoking paid inference.
Jev, a probabilistic logic programming system, is being integrated into DeepClause and its Pi extension to enable deterministic routing and decision-making in agent applications. The integration allows developers to build DML/Prolog-based skills that combine LLM reasoning with logical predicates for improved speed and reliability compared to pure LLM approaches.
A multi-agent plugin for DeepSeek Harness routes tasks to specialized models for writing and review, with neither model deciding pass/fail outcomes. The system uses qualification probes, schema-enforced verdicts, and durable audit records to ensure work quality while minimizing context overhead in the calling conversation.