Glossary.
50 terms you'll meet again and again working with self-hosted AI agents. Concise definitions with cross-references.
A
AI agent
Software that uses one or more language models to autonomously plan and execute multi-step tasks via tool calls.
Air-gap
Deployment with no network connection to untrusted networks — typically no internet access at all.
Approval flow
UI pattern requiring human confirmation before an agent's tool call executes.
B
C
Caddy
Reverse proxy server with automatic HTTPS via Let's Encrypt. The easiest path to TLS on a self-hosted setup.
Cloudflare Workers
Edge serverless runtime running V8 isolates across 330+ Cloudflare data centres.
CVE-2026-25253
Critical 1-click remote code execution vulnerability in OpenClaw versions before 2026.2.10. CVSS 9.6.
D
Data residency
Regulatory or contractual requirement that data not leave a defined geographic or organisational boundary.
Docker Compose
Tool for defining and running multi-container Docker applications via a single YAML file.
Docker sandbox
Sandbox using a Docker container with filesystem mount and network policy controls.
E
Edge AI
AI workloads running close to where data is generated rather than in centralised cloud datacenters.
Embeddings
Numerical vector representations of text, images, or audio that capture semantic similarity.
EU AI Act
EU regulation classifying AI systems by risk level and imposing obligations on high-risk deployments.
G
H
I
L
Llama
Meta's family of open-weight large language models. Llama 3.3 70B is the leading open frontier model in 2026.
llama.cpp
C++ inference engine for LLMs. The runtime under most local-LLM setups, including Ollama.
Local LLM
Language model running on local hardware rather than via cloud API. Llama, Qwen, Mistral local variants.
M
Magic link
Passwordless authentication where the user clicks a one-time link sent to their email.
MCP (Model Context Protocol)
Open standard for connecting language models to external tools and data sources via a JSON-RPC interface.
MCP server
Process that exposes a set of tools to MCP-compatible AI agents over a JSON-RPC interface.
Mistral
European LLM developer. Mistral 7B is the canonical small open-weight model; Mistral Small 22B targets the mid-tier.
Moltworker
Cloudflare Workers-based self-hosted AI agent reference implementation.
N
O
Ollama
Local LLM runtime that exposes an OpenAI-compatible API over local model weights.
OpenClaw
Open-source autonomous AI agent created by Peter Steinberger in November 2025. Most-installed self-hosted agent of 2026.
OpenRouter
LLM API gateway providing a unified interface across Anthropic, OpenAI, Google, Mistral and many open models.
P
Phi-3
Microsoft's small-language-model family. Phi-3 mini 3.8B runs on a Raspberry Pi 5.
Pocket AI
Self-hosted AI agents and language models running on portable, low-power hardware you own.
Prompt injection
Attack technique where adversarial input embedded in a document or webpage hijacks an agent's behaviour.
Q
R
S
Sandbox
Isolation layer that constrains what an agent's tool execution can access on the host.
Sandboxed tool execution
Running an agent's tool calls inside an isolated environment that limits filesystem, network and process access.
Self-hosted AI
AI software you install on hardware you control, rather than consuming as a hosted product.