Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.
-
Updated
Oct 12, 2026 - JavaScript
Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals.
Blazing fast, self-hosted structured decisions for open models with a TypeSafe AI compatible API, written in Rust.
Local Codex tool-output filtering with OpenAI Decisions by default and optional TypeSafe Jev support.
Guias, programação e referências em português para o DevDay Exchange Community Meetup Rio 2026 · Dots · Decisions API + TypeScript · Codex
Jev (TypeSafe) vs OpenAI Decisions API as RPG NPCs: 240 battles, simulation-scored decisions, confidence calibration, and a replay viewer that shows each AI’s “inner voice”.
Open models and one server for the Decisions API. Typed, calibrated decisions over text, images and video, local or hosted.
Guardian stops UPI and 'digital arrest' scams at the moment of payment. Built on OpenAI DevDay 2026: Decisions API, GPT-6.1 Sol, ChatGPT plugins (MCP + plugin extensions), Agents API, Dots.
Benign vs malignant skin-lesion classification with the OpenAI Decisions API, evaluated on HAM10000
Typed Decisions in real Chromium: Luna vs Jev, fresh evidence, server-verified synthetic workflows.
A DeepSeek Harness plugin to use OpenAI decisions API
A curated list of resources, tools, and community projects for OpenAI Decisions API
A small application for documenting architecture decisions. It provides a Flask/Jinja web interface, a JSON API, and 22 MCP tools for agents. SQLite stores projects, decisions, states, tags, comments and relations.
Google Chrome Extension to filter out YouTube content by thumbnail image, description, or custom keywords
DemoPilot: turns a project brief into a timed, evidence-aware live demo plan using the OpenAI Decisions API
A local-only rubric grading workspace with customizable decision models and optional AI explanations.
System 0 for your LLM: learns the fixed-choice answers your LLM gives (intents, routing, moderation) and serves the repeats in microseconds from a small CPU table, at most 5% disagreement, certified. Zero-code proxy for the OpenAI Decisions API, System One and chat models.
To associate your repository with the decisions-api topic, visit your repo's landing page and select "manage topics."