Havuz

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

Godot automation for AI agents to build and verify projects through a CLI, Agent Skill, or MCP server, with structured results, headless ope

Browser engine for agents. HTML in, structured Semantic Object Model out. Native MCP and AWP with a supported CDP subset. Apache-2.0.

Coding agent’lara TypeSafe AI Jev ile typed decisions ve calibrated confidence kullanmayı öğreten, topluluk projeleri ve code sketch’leri içeren bir agent skill’idir.

Neden yükseliyor · İki günlük yaşında 69 yıldız almış; bu erken ilgiye işaret ediyor. Ancak son commit ve farklı yazar verisi ölçülmediğinden ilginin kaynağı ve proje aktivitesi hakkında daha güçlü bir çıkarım yapılamaz.

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.

Schema-first structured extraction from LLMs — validated JSON from one call or a 150-page document.

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

Turn documents into structured JSON with local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.

A production-grade control layer that sits between your application logic and any LLM — input validation, schema enforcement, circuit breaki

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

Turn domain experts into production AI agents.

Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails

Make forms easier, LLM tools safer. Natural-language quantities, units, dates & ranges parsed into canonical values — zero dependencies, two

Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients

Structured output generation for LLMs in Node.js — token-level constraints for local models, native JSON modes for cloud APIs

Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text gene

Qwen3.6 vLLM Toolkit — Launcher + Templates, Optimized for 2×24 GB. vLLM launcher with an optimized hybrid chat template drawing from the be

Deuz SDK, TypeScript ile model entegrasyonları, agent ve swarm çalıştırma, memory ve retrieval gibi yetenekleri tek framework'te sunuyor.

Neden yükseliyor · 118 günlük yaşına rağmen 697 yıldız ve son 28 günde 126 commit dikkat çekiyor; ancak farklı yazar sayısının 1 olması, bu hareketliliğin tek geliştiriciden geldiğini gösteriyor. Yükselişin özel nedeni mevcut verilerden bilinmiyor.