I gave every agent in Magpie a LayerFS worktree 🌿
magpie-layerfs: 8 tools (provision / fork / checkpoint / publish / exec …) plus a trajectory page that replays each agent's checkpoints in that agent's own colour. Forks copy 0 bytes; checkpoints dedup into one store; publishes land on main as new Layers.
Native backend verified against the real LayerFS engine. PR open to magpie-community/plugins.
https://t.co/VVmOvXTcKV
🚀 CAD2GIS — DWG/DXF → GIS for AI agents — is now on the official MCP Registry & Glama.
Evidence-first conversion: entity census, semantic mapping, geometry/topology validation, QGIS delivery. Open source, Apache-2.0.
https://t.co/8HufHAXKSf
LayerFS v1.0.0 is out 🎉 Open-source (MIT)
Recursive filesystem for AI agents.
6 core ideas:
1. Ephemeral computing: agents spend ~80% thinking, so each Bash call mounts a Workspace, then commits
2. Decentralized agents: every agent commits to one Store, no DB server
3. Multiagent coordination: every tool call is a Commit; same-file clashes refused
4. Recursive filesystem: forks copy no files, at any depth
5. Ultra storage: dedup, then compression: 10 copies → 0.31
6. Instant bootstrap: ignored files stay in every Commit. ~5 min install vs 0.05 s mount
And 4 more:
7. Auto checkpoints: fork from any step
8. Append-only objects: content-addressed, never rewritten
9. .lww: lockfiles and caches take the newest edit
10. Big file, small edit: a write keeps only its bytes
Here are our links:
github: https://t.co/hwcUUBzhYw
website: https://t.co/8LInNxyN77
Watch the video below, and have Fun!!!