Skip to main content

NLSQL's internal AI coding agent CLI tool for interacting with codebases

Project description

NLSQL Internal Coding Agent

NLSQL's internal coding agent is a private, tool-driven, workspace-aware AI system designed to help with both internal and client-based development tasks in the NLSQL ecosystem.

Features

  • User-friendly command line interface.
  • Wide array of LLM/provider support acorss many cloud ecosystems.
  • Primary privacy & security focus.
  • Parallel tool calling ability for speed and efficency.

How it Works

The agent operates using a ReAct-style loop. A user submits a prompt, and the agent processes it by reasoning about the task, performing actions using available tools, and evaluating the results.

If the outcome is insufficient or incomplete, the agent continues this cycle, refining its approach and taking further actions until it can produce a final response.

Usage

To use the application, follow the steps below:

  1. Clone this repo to your local system: git clone <repo-link-here>
  2. Make sure you are at cd internal-coding-agent
  3. Create a virtual environment: python3 -m venv .venv
  4. Activate the venv: source .venv/bin/activate
  5. Install requirements: (if venv is activated correctly you should see "(venv)" in your terminal) pip install -r requirements.txt
  6. Add .env file into cd internal-coding-agent root folder
  7. Run the application: python3 run.py -u --workspace path/to/your/project

Arguments

Short Long Description Defaults to Required
-w --workspace The root directory of the project you want to work on. .
-u --usage Displays usage data after each conversation turn (input & output tokens) False

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nlsql_coder-0.0.1.tar.gz (13.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nlsql_coder-0.0.1-py3-none-any.whl (17.2 kB view details)

Uploaded Python 3

File details

Details for the file nlsql_coder-0.0.1.tar.gz.

File metadata

  • Download URL: nlsql_coder-0.0.1.tar.gz
  • Upload date:
  • Size: 13.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for nlsql_coder-0.0.1.tar.gz
Algorithm Hash digest
SHA256 6d456755552fdc2712d5ee3cbfaf5c7928e034d7f0b100828213554fda8ea56e
MD5 f13c26f88f2bc4a42f3a5a54ddca5bc5
BLAKE2b-256 58ce32141e534f04e5ed6f6f9f2a716a22fb9b8c0d9038435c7dec2730675a1b

See more details on using hashes here.

File details

Details for the file nlsql_coder-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: nlsql_coder-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 17.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for nlsql_coder-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ab99750c08146a3502ed94bb8079a3f315519410a098561aedb11db7a0048260
MD5 14307c3bb337b1194d68d576cf0ff880
BLAKE2b-256 65b23991c0ae9916ee0e6c44775666f58f61cf9e81ab6015d595768ab7e72840

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page