Quickstart
This page assumes you have already followed the Installation steps and have at least one provider authenticated.
1. Bootstrap the workspace
In any project you want Lime to work on, run:
lime initlime init writes:
- An
AGENTS.mdyou can edit to describe project conventions. - A
.lime/directory used for per-directory context, sessions, and local settings. - A
.lime.jsonfile for shared (committable) repo defaults. - The relevant
.gitignoreentries so machine-local state doesn’t leak.
2. Start the REPL
limeThe REPL boots with the workspace’s AGENTS.md, project .lime/
instructions, and any user-level memory loaded automatically. Tokens stream
character-by-character, tool calls render inline, reasoning summaries
collapse and expand, and Lime prompts before any side effect.
> find every TODO and group them by file
Searching workspace… ✓ glob_search **/*.rs (124 files) ✓ grep_search "TODO" (12 hits in 7 files) ✓ read_file src/auth.rs
## TODOs by file
**src/auth.rs** (3) - line 42 — TODO: add refresh-token rotation …3. Useful keystrokes
| Key | Action |
|---|---|
/ | Open the slash-command palette (fuzzy matched). |
! | Drop into a one-shot shell line — stdout is persisted as a session message. |
↑ | Recall previous prompt. |
Esc | Cancel the current turn. |
4. Pick a model
lime --model claude-opus-4-7lime --model o4-mini --reasoning-effort highlime --model pro # alias for gemini-2.5-proOr persist your choice in .lime/settings.local.json:
{ "model": "claude-opus-4-7" }The default model when none is set is gpt-5.4. See
Models & providers for the full catalog.
5. Try non-interactive mode
You don’t have to start the REPL — you can run a single slash command non-interactively against the most recent session:
lime --resume latest /statuslime --resume latest /commitFor a full programmatic workflow, see Non-interactive use.
6. Where to next
- Your first session — a guided tour of what loads when you start Lime, plus the permission flow.
- Permission model — the five permission modes Lime ships with.
- Slash commands — the built-in command registry.
- Built-in tools — what the agent can do, and how permissions gate it.