Skip to content

issues Search Results · language:Dune language:Python language:JavaScript language:JavaScript language:Python language:C#

Filter by

46.6M results  (697 ms)

46.6M results

Context The store needs a human surface — one place to see and act on every task, and a tasks section in the daily brief. There s no separate todo agent ; the store + these surfaces are the product. ...
agent-hub-layer
enhancement
gui
p1

See: https://github.com/foundryvtt/dnd5e/pull/6667
category: ui
system: activities
system: items

Context The store is only valuable if the producing agents actually file tasks into it with a link back to what created them, and don t create duplicates on re-sync. Goal Wire the task-producing agents ...
agent-hub-layer
enhancement
p1

Goal Use Njord budget-update proposals as the first concrete implementation of cross-agent decision metrics and preference learning. Motivation Njord should learn how the user budgets by observing which ...
enhancement

Goal Give users a UI surface for seeing how well agents align with their decisions and for safely configuring auto-approval thresholds. Scope - Show approval, rejection, edit, deferral, auto-approval, ...
enhancement

Context Any agent should add task management by name, the same way it composes rag or memory. Goal A TaskToolsMixin exposing task tools, registered as tasks in KNOWN_TOOLS. Scope / Deliverables ...
agent-hub-layer
enhancement
p1

Goal Allow users to opt into auto-approval for low-risk, high-confidence agent decisions while preserving explicit controls, auditability, and safety limits. Scope - Define auto-approval policies ...
enhancement

Context The single source of truth for the user s to-do list, written and read by many agents. Core framework infrastructure (sibling to MemoryStore/GoalStore). Goal A TaskStore backed by SQLite that ...
agent-hub-layer
enhancement
p0

Goal Let Mongoose learn user decision preferences from approvals, rejections, edits, and reversals without allowing agents to silently take over important work. Scope - Define preference signals agents ...
enhancement

Goal Record how users respond to agent proposals so Mongoose can measure alignment between agent decisions and user preferences over time. Scope - Track proposal outcomes: approved, rejected, edited, ...
enhancement
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! Restrict your search to the title by using the in:title qualifier.