Quickstart¶
This assumes Collie is installed. Every example runs locally.
Zero-config¶
collie # terminal chat (TUI); the first run picks a provider
collie web # browser GUI — chat, the live verification gate, diffs, the star-map
collie app # the native desktop window (Windows)
Your first verified fix¶
Point Collie at a real bug with a cheap model:
Watch the verification gate: it writes a reproduction that fails, makes the smallest edit, and re-runs it. The run ends verified ✓, not "done."
Fully local, no key¶
Machine-readable output¶
collie run "fix the bug" --json # final result object (tokens, cost, verified)
collie run "fix the bug" --stream-json # live NDJSON: tool · edit · repro-gate · receipt
Autonomy that ends on green¶
# iterate toward a goal; STOP the first turn a real executed check passes
collie loop --goal "get the suite passing" --until "pytest -q" --max 8
The loop terminates on a real executed check (--until exits 0), not on the model announcing it's
finished — the verification gate, one level up.
Best-of-N by what actually passes¶
# run 3 isolated attempts, keep only what passes --check; apply nothing if none pass
collie pack "fix the failing test" -n 3 --check "pytest -q" --apply
Warm a repo (optional)¶
collie init # pre-download the memory model for this repo
collie init --rules # additionally have the model write an AGENTS.md
collie init is optional — the first question pays the indexing cost otherwise. Collie reads
AGENTS.md / CLAUDE.md as project rules on every run.
Where next¶
- Connect your preferred model → Providers
- Every flag and subcommand → CLI reference
- The native window, wallpaper, and browser bridge → The desktop app