DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run a local agent in your terminal with approval controls with Nosis

Install Nosis and chat with a personal agent in the terminal, limited to one workspace folder.

Credentials. The API key goes into ~/.nosis/.env, so keep that file out of shared folders and version control.

Who it is forA developer who wants an AI agent that works on files in a project folder and asks before risky actions.

The problemChat tools without local file access cannot act on a project, and agents with full access can change files without review.

The outcomeA working TUI session in your chosen folder, with the default provider configured and session data saved under ~/.nosis/.

What you need first

  • Python 3.11 or newer
  • Node.js 22 or newer
  • uv installed
  • An API key for the default provider, such as OPENAI_KEY

Steps

  1. Install Python 3.11 or newer, Node.js 22 or newer, and uv, then run git clone https://github.com/EvannZhongg/Nosis.git and cd Nosis.
  2. Run npm install and then npm run build inside the Nosis folder.
  3. Run uv tool install --editable ".[gui]".
  4. Change into your project folder and run nosis once, then quit.
  5. Create ~/.nosis/.env with the line OPENAI_KEY=your-api-key, then run nosis again.

Prompt for your agent

Using the Nosis repo at https://github.com/EvannZhongg/Nosis, follow its Quick start to install the TUI, then launch `nosis` from <workspace path>. Report whether ~/.nosis/ was initialized and which permission preset the session starts with. Verify that file tools are limited to <workspace path>.

Caveat. Shell commands run in the workspace sandbox or the host environment depending on scope, so choose the permission preset deliberately before giving the agent broad access.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page