Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Docker
Running Deep Agents in a Local OpenSandbox Backend
How to wire OpenSandbox into Deep Agents through BaseSandbox, bridge sync and async code, and run a data analysis agent safely in a local Docker sandbox.
15 min readHow a Docs-Fixing AI Agent Fooled Itself: False Positives in a Docker Sandbox
A LangGraph docs-fixing agent shipped a no-op fix, then broke on src-layout packages. The Docker sandbox bug behind it and the real fix it found in click.
7 min readSeven Questions to Ask Before Running a Local MCP Server
A checklist for sandboxing local MCP servers, worked through on the GitHub server: short-lived tokens, sealed network, egress allowlist and pinned tool lists.
8 min readSerena MCP Server: Symbol-Aware Code Editing for AI Assistants
Set up Serena with Docker and SSE so Claude Code, VS Code and OpenCode get LSP-backed symbol search, safe renames and persistent memory with fewer tokens.
9 min readHermes and Obsidian: A Three-Agent Knowledge Vault with Human Review
Set up an orchestrator, researcher and librarian in Hermes that move notes from Bronze to Silver to Gold in an Obsidian vault, with Docker isolation and review.
7 min readRun the Neo4j MCP Server on Your Own Machine with Docker and VS Code
Self-host Neo4j and its official MCP server with Docker Compose, secure it with Basic Auth over HTTP, connect VS Code in Agent mode and query a demo graph.
8 min readFixing Ollama Connection Refused on WSL2 and Wiring Up Dify and vLLM
Ollama works in WSL2 but Dify gets connection refused? Trace the bind address, set OLLAMA_HOST, add a portproxy, and avoid the Docker localhost trap when linking vLLM.
7 min readConnect Private GitHub Repos to Claude Desktop With a Token and Docker
Create a classic GitHub token with safe scopes, add the GitHub MCP server to Claude Desktop through Docker, test it, and use it for PR review, triage and changelogs.
5 min readAnythingLLM “Model Not Found” with Ollama: Five Plumbing Fixes
AnythingLLM says model not found with Ollama? It's usually HTTP wiring, Docker networking or tag mismatches, not broken weights. Five fixes, checked in order.
11 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.