Installing OpenClaw on Linux (the Real Walkthrough)
A real npm install of OpenClaw 2026.5.28 on Debian: dodging EACCES, the full CLI surface, and the point where it needs your accounts.…
Sign up to LLMbits!
Hands-on AI tutorials and honest tool reviews - agents, local LLMs, MCP servers, and the dev stack - written as I learn them. For builders and the AI-curious.
Installing Hermes Agent on Linux (the Real Walkthrough)
A real pip install of Hermes Agent v0.15.2 on Debian: the python3-venv gotcha, the full command surface, and where the install ends and your account begins.…
MCP Servers Worth Running: The Official Set, Tested
I installed the official reference MCP servers and listed what each actually exposes. Which earn a slot (filesystem, git, fetch, memory, time) and which do not.…
Build Your First MCP Server in Python (and the Security Section Everyone Skips)
A one-file MCP server in Python with uv and FastMCP, verified on SDK 1.27.2 with real output, plus the path-scoping security section other tutorials skip.…
MCP vs Function Calling: When Each One Wins
They are not rivals. The one difference that matters, a 30-second decision rubric, and three worked examples for choosing between them.…
What Is an MCP Server? Explained as Simply as Possible
Client, server, protocol: the three words everyone mixes up, pulled apart. MCP primitives, transports, and how a session works, in plain English.…
Build llama.cpp From Source for CPU Inference
Build llama.cpp on a CPU-only Debian box, run llama-bench for real numbers, and serve an OpenAI-compatible endpoint. With a 4.8GB gotcha.…
Run Your First MCP Server: Filesystem, Step by Step
Run the official filesystem MCP server and drive it by hand with JSON-RPC. See initialize, tools/list, and tools/call on the wire.…
Open WebUI + Ollama in Docker: a Local AI Chat UI
Run Open WebUI in Docker as a local ChatGPT-style UI over Ollama: the exact command, the host-gateway fix, and gotchas to skip.…
Run a Local LLM with Ollama on Debian (CPU-Only)
Install Ollama, pull a model, and benchmark CPU-only inference with real tokens/s numbers from an old 6-core Xeon.…
Run Claude Code From Your Phone: The tmux + SSH Setup
Tested with: tmux 3.2a on Ubuntu 22.04, Claude Code (latest stable as of 2026-05), Termius on iOS,…
Explore topics
View all