A docker compose for getting letta server to work with my local setup
State of My Homelab 2025
An overview of my current homelab architecture, focusing on a transition from complex orchestration to a simplified Docker Compose-based setup.
plugin.mjs at d5e940eb6d5b67444f8a8e68ba8c7bdb648601a7 · hollis.pds.garlic.town/letta-mesh
Peer-to-peer cross-agent messaging channel for Letta Code, built on Iroh.
[Feature Request] Support for Apple's Linux containers on macOS · Issue #1335 · abiosoft/colima
Description ref: https://github.com/apple/containerization https://github.com/apple/container
Benjamin Marie (@bnjmnmarie)
A new alternative to Ollama: You can now run models directly through Unsloth (with Docker): https://docs.unsloth.ai/models/how-to-run-llms-with-docker It supports the same models as llama.cpp, which I guess means it runs on llama.cpp… But this way you don’t need to set up anything, if you already have Docker installed.
README.md at d5e940eb6d5b67444f8a8e68ba8c7bdb648601a7 · hollis.pds.garlic.town/letta-mesh
Peer-to-peer cross-agent messaging channel for Letta Code, built on Iroh.
Agent54/xe-orchestrator
the docker orchestrator for the dev mode of darc/xenon this includes the docker dev domains, local agent containers and vscode server
mods/mesh-tools.ts at d5e940eb6d5b67444f8a8e68ba8c7bdb648601a7 · hollis.pds.garlic.town/letta-mesh
Peer-to-peer cross-agent messaging channel for Letta Code, built on Iroh.
Should I Run Plain Docker Compose in Production in 2026?
Yes, plain Docker Compose can still run production workloads in 2026—if you close the operational gaps it leaves: cleanup, healing, image pinning, socket security, and updates.
Docker Brings Compose to the AI Agent Era | Docker
Define, run, and scale AI agents using Docker Compose and Docker Offload. Streamline agentic development across your stack.
