#task-management

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

A Claude Code skill — single source of truth for deferred work. Don't lose track of what you've punted.

Universal collaboration protocol + CLI for multi-agent LLM teams — Claude Code, Reasonix, Codex, WorkBuddy, Cursor

Agent-friendly CLI for Dida365 / TickTick

SmartWork 360 — task and performance management for government offices, built with Next.js 14 and strict TypeScript

Local-first kanban board where Claude Code agents work your cards — dependency chains with merge gates, an AI manager that reviews real diffs and merges green PRs, group lanes, CI-gated. One runtime dependency.

Assign real work, share context, review output, and keep every human-agent handoff visible.

AgentBridge — an OpenClaw coordination dashboard and API for assigning, tracking, and reviewing work across AI agents.

Trello skill pack for Claude Code and Codex over the Trello REST API - boards, lists and cards end to end, a status digest for a board, and a radar for what is due across every board. A free tool by DBHQ.

Platform-specific agent skills for working with Operon through the Operon CLI and Agent Runtime.

Git-native shared context for teams whose members each use their own AI coding agent (Claude Code, Cursor, Antigravity, OpenCode...) on the same repo

Your agent's work survives the session that wrote it. Task state as files in your repo, where the location is the status. A Claude Code plugin.

Open-source Claude Code assistant that turns your notes into a personal chief of staff: capture notes, track follow-ups and deadlines, get priority alerts, and ask your notes questions.

AI 任务流转台: turn rough ideas into structured AI coding tasks, generate Codex or Claude prompts, and backfill execution results.

SQLite-backed task coordination for AI agents. No server. No daemon. No queues. Just a shared database file agents use to claim, track, review, and complete work.

Menu-bar task board for AI coding agents — persistent, per-project, via a neutral protocol. Works with Claude Code, Codex, any agent.

Task-completion enforcement for Claude Code. An external task ledger plus a Stop-hook gate that refuses to end a turn while recorded work is still outstanding.

Harvest todos from agent memory & rule files (AGENTS.md / CLAUDE.md / memory dirs) into a real, checkable task list — noise control, project attribution, loss-proof verdicts · 记忆待办归集

LeadMode: Congratulations, you're the tech lead now. Turn tickets into planned, delegated, verified agent work.

A Claude Code status line for people using Tasqr for intelligent task tracking.