Durable MCP control plane for long-running Codex Desktop tasks
-
Updated
Sep 9, 2026 - Python
Durable MCP control plane for long-running Codex Desktop tasks
A runnable TypeScript tutorial that builds a minimal DeepSeek-style agent harness from scratch.
DyroEngineeringFlow 是面向多仓团队的本地优先工程自动化与交付控制平台。它将开发线、Git worktree、任务编排、 Agent 启动、质量门禁、独立复核与合并审计统一到可版本化配置中,帮助团队从任务创建到交付合并形成清晰、安全、 可追溯的自动化流程。日常通过简洁命令 dyro 即可完成初始化、环境检查、任务执行与协作交付。
Keep long-running Codex tasks moving across fresh context windows with validated cumulative handoffs.
Long Long Run (LLR) is a plug-and-play Codex skill for serious long-running agent tasks: an agent-first harness runtime with INC intent-noise cancellation, ACTIVE durable mainlines, side-thread tolerance, and Codex hook-enforced stop guards.
Multi-agent harness for long-running AI application development. Planner-Generator-Evaluator architecture with progressive simplification. Claude Code plugin.
Durable execution where agents, services, and humans coordinate as equals. Open protocol + managed cloud.
Async DeepSeek Harness delegation for Codex: run scoped long-running writing, coding, research, and review tasks in parallel with durable status and safe result collection.
Create custom AI agent harnesses for any repository using this CLI generator.
Local-first watchdog and Codex skill for stalled tool calls, long-running task monitoring, oversized-thread diagnosis, bounded cleanup, and safe handoff recovery.
一个 7×24 小时不间断运行,帮你跑实验、用 Git 维护公开仓库、更新 LaTeX(Overleaf)论文的科研自动化工作流。实测效率提升 25 倍。Claude Code Skill,一条命令装进任意项目。
Self-hosted AI agent harness in Rust, built for long tasks: a virtual session keeps work coherent across context compaction & restarts. Telegram/Discord, durable queues, fail-closed permissions, Codex/OpenRouter routing, a JSONL receipt for every step. 6 deps, no async runtime, Windows-first.
macOS menu bar app that keeps the Mac awake during long-running agent tasks (Swift + IOKit)
Keep Codex long tasks running while you sleep: local compact/context recovery with audited bundles and safe one-relay handoffs.
Long-running AI agents on Cloudflare's serverless edge. Each agent is a Durable Object with its own SQLite, so streams resume, turns survive deploys, tasks run for hours and humans approve mid-run, with no queue, workflow engine or database to operate. Agents SDK + Vercel AI Gateway + AI Elements.
面向 Codex 的跨会话编码 Skill:可恢复检查点、版本绑定证据与独立审查。
中文 Agent Skills 技能包:工程纪律四件套(会话交接/进度锚/项目地图/不可逆变更) + AI 音乐生产 + 中文网文流水线 | Chinese agent skills: long-project discipline + creative pipelines
Claude Code skill for orchestrating long-running, multi-session development campaigns
Windows 保持电脑运行和不休眠工具,支持电脑息屏/熄屏运行、锁屏继续运行、项目夜间运行、ChatGPT、Codex 及 AI 长任务后台持续运行。Keep Windows awake while allowing the display to turn off.
Run long Codex commands with a clean low-effort monitor and hourly checkpoints.
To associate your repository with the long-running-tasks topic, visit your repo's landing page and select "manage topics."