$ cat /var/log/thoughts

Developer Tools + Self-Hosting

Posts matching all selected tags.

Filters2

7 posts

Claude Cowork vs OpenClaw is a permission model fight

claude cowork vs openclaw is a permission default. Cowork stays in a folder and still asks to delete. OpenClaw ships host exec with ask off. Pick the disk.

Strong OpinionsClaude DesktopSecurityAI CodingOpen SourceSelf-HostingDeveloper ToolsClaude Code1 min read · Aug 25, 2026

OpenClaw vs Claude is not a coding agent bakeoff

OpenClaw vs Claude is a category error. One is a session with a permission dialog. The other is a host Gateway with ask off. Read the docs before you pick.

Strong OpinionsAI CodingClaude CodeSecurityOpen SourceCoding AgentsSelf-HostingDeveloper Tools1 min read · Aug 25, 2026

Qwen 3.8 overthinks on the default reasoning setting

Qwen 3.8 overthinks on the default xhigh setting. A pelican SVG ate 22,276 thinking tokens and 21 minutes. Start on low or off, then raise it for hard jobs.

Strong OpinionsAI CodingDeveloper ToolsSelf-HostingOpen SourceTrend Commentary1 min read · Aug 21, 2026

The Self-Hosted Developer Stack: Cancel Everything, Own Everything

Self-hosted developer tools in 2026 replace $200+/month in SaaS with a single $20/month VPS. After migrating 8 services off managed platforms, here is every tool, the migration difficulty, and what to skip.

Worth UsingDeveloper ToolsSelf-HostingLinuxDockerProductivityDevOps1 min read · Apr 11, 2026

Gemma 4 Is Google's Best Open Model Yet (Here's How to Use It)

Gemma 4 ships Apache 2.0, 256K context, and four model sizes. Benchmarks beat Llama 4 across the board. Quick use cases with Ollama and Transformers code.

Strong OpinionsAI CodingMLOpen SourceSelf-HostingDeveloper Tools1 min read · Apr 10, 2026

Self-Hosting AI for Code: The $0/Month Developer Stack

Build a complete self-hosted AI coding stack with Ollama, Continue.dev, and Open WebUI for $0/month. Includes hardware requirements, cost math, and the setup commands.

Build AlongAI CodingSelf-HostingDeveloper ToolsCLIProductivity1 min read · Apr 10, 2026

How to Run Claude Code With Local Models

Run claude code local models with Ollama, LM Studio, or vLLM. Set three environment variables, point at your local server, and code with zero API costs.

Build AlongAI CodingClaude CodeSelf-HostingDeveloper ToolsCLI1 min read · Apr 1, 2026