DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks. Code, paper and blog post.
-
Updated
Oct 19, 2026 - Python
DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks. Code, paper and blog post.
RTGL is a Python framework for task generation in Relational Deep Learning. It provides a Relational Task Generation Language to simplify task generation when working with complex static/temporal relational data.
Convert GitHub repos into long-horizon reverse engineer tasks
This repository consists of a set of files designed to generate random periods and task sets.
Scale validated computer-use RL tasks from real PowerPoint decks
Agent-guided generation and evaluation of editable presentation repair tasks, informed by real model rollouts.
An AI-powered project planning assistant that transforms unstructured software requirements into structured project plans, tasks, estimates, and development workflows.
Website for trigonometry tasks generation
CLI tool that fetches unresolved SonarQube issues and turns them into grouped, effort-estimated markdown tasks for backlog/work tracking.
Task Gate — agents propose manipulation tasks, a verification gate keeps the valid ones. Built on the Genesis SDK; 1.45M env-steps/s on Apple Metal.
Experimental code and selected traces for automatic task discovery and verification
To associate your repository with the task-generation topic, visit your repo's landing page and select "manage topics."