Skip to main content

NebulaCode — AI coding assistant for the terminal

Project description

Nebula Code

AI coding assistant for the terminal — like Claude Code or Codex, but runs on your own local models via Ollama or a NebulaX instance.

nebula › explain the auth flow in this repo
nebula › add input validation to src/api/users.py
nebula › write tests for the payment module and run them

Install

pip install nebulacode

Or from a downloaded wheel:

pip install nebulacode-0.13.0-py3-none-any.whl

Requirements

  • Python 3.10+
  • Ollama running locally (ollama serve)
  • A model: ollama pull llama3.2 or ollama pull codellama

Quick start

nebula                   # start interactive session
nebula -m codellama:7b   # use a specific model
nebula models            # list available models
nebula set model codellama:7b   # save default model

Session commands

Command Description
/clear Clear conversation and screen
/context Show conversation history
/model NAME Switch model
/set KEY VALUE Change max_steps or temperature
/tools List available tools
/help Show help
/exit Quit

Tools

Tool What it does
read_file Read any file
write_file Create or overwrite a file
patch_file Targeted string replacement
list_files List a directory
run_command Run shell commands (tests, linters, builds)
search_files Grep across files

Remote daemon mode

Connect to a NebulaX server and let the web UI dispatch tasks to your machine:

nebula login https://your-nebulax-server   # authenticate
nebula daemon                              # start listening

The NebulaX Chat UI will show a "CLI" badge — select your connected machine and the AI will execute tasks locally and stream results back.

Configuration

Stored at ~/.nebula/config.json.

nebula config                            # show config
nebula set model codellama:13b           # default model
nebula set max_steps 30                  # allow longer runs
nebula set ollama_url http://host:11434  # remote Ollama

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

nebulacode-0.13.0.tar.gz (1.9 MB view details)

Uploaded Source

Built Distribution

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

nebulacode-0.13.0-py3-none-any.whl (25.7 kB view details)

Uploaded Python 3

File details

Details for the file nebulacode-0.13.0.tar.gz.

File metadata

  • Download URL: nebulacode-0.13.0.tar.gz
  • Upload date:
  • Size: 1.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nebulacode-0.13.0.tar.gz
Algorithm Hash digest
SHA256 c935fefb1d88b09ed250a56081070b5dd21cecf87236b639d873729fdf50e319
MD5 b44b27dc8db7adec1b093bfbcb30e983
BLAKE2b-256 9948fe8f5b552c495611db586ff79a77c8971ccba90f77bc6c9b38ba365767f9

See more details on using hashes here.

File details

Details for the file nebulacode-0.13.0-py3-none-any.whl.

File metadata

  • Download URL: nebulacode-0.13.0-py3-none-any.whl
  • Upload date:
  • Size: 25.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for nebulacode-0.13.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0f7d6abee6a05fca56804a2509a3f8f7ed1f14d95888ab7a859e13920356a19e
MD5 76d8baf4a60aa82db80dc1cab096f52d
BLAKE2b-256 134f61058ce0fc63adb869c02650098ade0c22a0a4c9d7cbe3c97394f9fe29bc

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