#93 · Primary category： AI Agents & Automation
planning-with-files
Persistent file-based planning for AI coding agents that survives context loss, /clear, and compaction via per-turn re-injection.
Project last updated：08/29/26
GitHub Stars
26.4K
Forks
2.2K
Contributors
52
License
MIT
Why we included this project
Long agent sessions have a way of losing the plot. A /clear or a context compaction wipes the working memory, and the plan you spent an hour building is gone. This skill keeps task_plan.md, findings.md, and progress.md on disk and re-injects them every turn, so the plan survives crashes, /clear, and compaction. It is a lightweight pattern you install as a skill rather than a framework, and it works across 60+ agents through the Agent Skills standard. Teams running multi-step tasks with coding agents get a deterministic completion gate on top, which makes it easier to trust that long-running work actually finished.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.