Aurora

A micro terminal coding agent — small enough to read, complete enough to use every day. Named after my beautiful two-year-old daughter Aurora, always with her hair bow.

Aurora is a coding agent that lives in the terminal. You talk to it in plain text; it reads and edits files, runs commands and searches the web through a tool loop — always asking before it changes anything. Drop into a persistent bash shell or its built-in editor without ever leaving the session. It was built from scratch in Python as an exercise in understanding how agents like Claude Code actually work, and grew into a daily tool.

Source on GitHub Aurora just after boot: the bootstrap brief (rules read, context indexes clean), a /model pick with live pricing, and a chat exchange

Main features

Aurora's secret-detection challenge, catching an AWS key, GitHub token, Bearer token and UUID in a file before it reaches the model

Privacy & security at the core.
- Every prompt and every tool output — even read-only ones like read_file/grep — is scanned for API keys, tokens and credentials before it reaches the model or the session log. A match lets you redact it, keep it, allow it going forward (remembered, never flagged again), or stop.
- API keys never touch disk in plaintext — OS keyring or encrypted storage only.

Approval-gated, steerable edits.
- Every file write, edit or shell command shows a diff preview and asks first; trusted patterns can be allowlisted.
- Don't just allow or deny — pick "Comment" and type a note instead; Aurora folds it into the same request and redoes the change, no deny → re-explain → re-approve round trip.
- Pick "Explain" instead, and Aurora describes what the change will do before asking again — no blind approvals.
- A shadow git snapshot is taken before every approved change, so /rewind can undo any step — even the rewind itself.

Aurora explaining what a proposed shell command will do before asking for approval again

Any model, zero friction.
- OpenRouter or a self-hosted llama.cpp server, switched from the same arrow-key /model menu — current model marked, no key stored yet? it asks once and remembers.
- Adding one is just pasting a URL: /model add https://openrouter.ai/<org>/<model> validates it against the OpenRouter catalog, fetches its context size, pricing and description, asks for your key if it's missing, and switches to it — no config editing. /model remove drops one just as easily.

Built for daily terminal use.
- Full-screen TUI: scrollable chat with streaming markdown, timed collapsible thinking blocks, mouse support and drag-to-copy — with a classic REPL fallback for plain terminals.
- Resume past conversations, export them as markdown, /compact long ones into a summary, or /remember what mattered into a persistent cross-session memory.
- Reusable prompt-driven skills, plus a per-project bootstrap prompt so the agent starts every session already knowing the codebase.
- Drop into a persistent bash shell — folder autocomplete, real cd tracking — without leaving the session.
- A built-in /nano editor for quick edits, no shelling out to a real editor.
- Built-in web_search/web_fetch tools when the answer isn't in your codebase.
- /cost shows a per-model token + $ breakdown, cache hits included.

Persistent bash mode in Aurora: cd tracked across commands, ls output linkified

Aurora using its web_search and web_fetch tools to answer a live weather question

Install

curl -fsSL https://raw.githubusercontent.com/ricardopsantos/Aurora/main/bootstrap-install.sh | bash

It runs on macOS or Linux, degrades gracefully when the local model server is unreachable, and the whole spec — requirements, build plan and test plan — ships in the repo.