FAQ
What can Vesper Code be used for?
Software development: Writing features, tests, and scripts across common languages and frameworks. It can also run CLI commands, adjust build configs, review code, and answer questions about your repo.
What model does Vesper Code use?
Multiple. In ChatGPT mode, Default uses GPT-5.3 Codex and Max uses GPT-5.5 for thinking-heavy work. In Kimi mode, agents use Kimi for Coding. Subagents are matched to their tasks, and Max mode runs multiple implementations in parallel. See What models do you use? for the full breakdown.
Is Vesper Code open source?
Yes. It's Apache 2.0 licensed.
Do you store my data?
We don't store your codebase. The server forwards requests to model providers. We keep small slices of chat logs for debugging.
Do you use model providers that train on my codebase or chat data?
No, we don't choose providers that will train on your data in our standard modes.
Can I trust Vesper Code with full access to my terminal?
You can use Docker for isolation to run Vesper Code against a scoped copy of your codebase.
Can I specify custom instructions for Vesper Code?
Yes. Add knowledge.md files to describe patterns, constraints, and commands. Vesper Code also reads AGENTS.md and compatible legacy instruction files if present. Per directory, it picks knowledge.md first, then the next supported instruction file. Vesper Code updates existing knowledge files but won't create them unless you ask.
You can also create a home directory knowledge file (~/.knowledge.md or ~/.AGENTS.md) for preferences that apply across all projects. File name matching is case-insensitive. See Knowledge Files for details.
Can I tell Vesper Code to ignore certain files?
Vesper Code by default will not read files that are specified in your .gitignore. You can also create a .vesperignore file to specify additional files or folders to ignore.
What if I want Vesper Code to not ignore some files in the .gitignore?
The .vesperignore follows standard .gitignore negation rules as well! So to ignore a file from git but not from Vesper Code:
path/to/file
!path/to/file
The final set of files ignored by Vesper Code are determined by the contents of .gitignore, followed by the contents of .vesperignore.
How does Vesper Code work?
Vesper Code runs specialized models in parallel: one finds files, another reasons through the problem, another writes code, another reviews. A selector picks the best output. In Max mode, multiple implementations compete. Benchmark comparison.
How does Vesper Code compare to other coding tools?
See Vesper Code vs Other Coding Tools for a detailed comparison. Short version: Vesper Code is fast, cost-aware, and handles large codebases well.
I have more questions!
Contact support@vespercode.com or join our Discord.