DeepSeek Harness Plugin

layerfs

Memory 2748 stars Resource

Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.

Project details

GitHub stars 2748
LicenseMIT
Primary languageRust
Last push2026-11-12T13:11:07Z
Added to this directory2026-10-22

Screenshots

About this project

Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.

More about this project

LayerFS is the substrate under your agents. Each one mounts a complete, writable

Project FAQ: layerfs

What is layerfs?

layerfs is a DeepSeek Harness ecosystem resource maintained by Ephemeral-AI-Lab. Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.

Where can I get layerfs?

Source code and usage instructions are available at https://github.com/Ephemeral-AI-Lab/layerfs. Follow the repository README for the correct setup steps.

Is layerfs free?

layerfs is a community open-source project released under the MIT license. Review the repository license and documentation before use.

EverOS

Resource 13895

Memory

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

View details → EverMind-AI GitHub profile image EverMind-AI

bisheng

App 12288

Memory

BISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.

View details → dataelement GitHub profile image dataelement