Concepts
Plain explanations of how kli works underneath: the agent loop, sessions, context, tools, the live image, permissions, profiles, models, and providers.
kli is a small live kernel; everything else — model providers, tools, the session log, the commands, the terminal interface — is an extension installed on it. For steps, go to Guides; for exact values, go to Reference.
- The live image — what it means that kli is one running image you can change without restarting it.
- Extensions all the way down — the mechanism said once: a small kernel, a retractable protocol, and the three pillars it buys you.
- The agent loop — what happens during one turn, and why a failed tool call comes back as a result the model can fix.
- Sessions as a tree — why a session is an append-only tree you can branch, rewind, and resume.
- Context and the system prompt — how your project files shape what the model sees.
- Tools and hashline edits — why edits are anchored patches that refuse to clobber a drifted file.
- Capabilities and fault barriers — how kli decides what a tool may do, and how it contains a misbehaving part.
- Security model and sandboxing — why kli enforces authority but not containment, and how to run it in a sandbox.
- Profiles — how a profile selects the set of extensions kli boots with.
- Models, providers, and transports — how kli talks to different model APIs.