Skip to main content

Autonomous coding agent with interactive planning and modular execution

Project description

OmniMe

OmniMe is your ultimate AI-powered assistant and intelligent agent, built to supercharge your development workflow. Whether you're brainstorming new ideas, writing complex features, or squashing bugs, OmniMe adapts to your needs with an incredibly flexible and powerful architecture.

Designed with freedom in mind, OmniMe seamlessly supports both cloud-based and local LLMs—giving you full control over your code and privacy. It shines exceptionally well with local models powered by Ollama, allowing you to harness state-of-the-art AI without leaving your machine.


Why Choose OmniMe?

🚀 Your Personal AI Agent OmniMe isn't just an autocomplete tool; it's a fully-fledged AI agent that understands your project context. It works alongside you to handle diverse coding tasks, from interactive planning to automated bug fixing.

🧠 Persistent Memory & Context Never repeat yourself. OmniMe features a persistent memory system that remembers your project's unique quirks, design decisions, and past conversations. It maintains focus, ensuring that the AI has exactly the context it needs, right when it needs it.

🛠️ Flexible, Skill-Based Architecture Tailor your assistant to your exact workflow. OmniMe uses a highly modular "Skills" system. Equip your agent with specific abilities—like web research, advanced refactoring, or custom scripts—allowing it to tackle different tasks seamlessly using specialized sub-agents.

☁️ Cloud or Local: You Decide Enjoy the best of both worlds. Connect to powerful cloud models or run completely offline with local LLMs. OmniMe is heavily optimized for Ollama, making it incredibly easy to run powerful open-weights models locally on your own hardware.


Getting Started

Installation

Install OmniMe directly via pip:

pip install omnime

Or run it from source:

git clone https://github.com/omnimedev/OmniMe
cd OmniMe
python -m venv .env
source .env/bin/activate          # Linux/macOS
# .env\Scripts\activate           # Windows

# Install OmniMe dependencies
pip install -r requirements.txt

Running OmniMe

OmniMe comes with a beautiful, integrated Web-Based GUI that works seamlessly across platforms:

python main.py

Don't like GUIs? OmniMe also supports an interactive CLI REPL and a headless JSON protocol server!


Deep Dive: How It Works

Curious about what powers OmniMe under the hood? Want to learn about our MemGPT orchestrator, shadow git versioning, and modular skill designs?

👉 Read the Technical Overview


Community & License

OmniMe is proudly open source and available under the MIT license.

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

omnime-0.2.8.tar.gz (13.8 MB view details)

Uploaded Source

Built Distribution

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

omnime-0.2.8-py3-none-any.whl (3.7 MB view details)

Uploaded Python 3

File details

Details for the file omnime-0.2.8.tar.gz.

File metadata

  • Download URL: omnime-0.2.8.tar.gz
  • Upload date:
  • Size: 13.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for omnime-0.2.8.tar.gz
Algorithm Hash digest
SHA256 295c5b15b83811dda83270ee1bcdcb4ac4ec18c93807cdbf2f4dbb589fdd41c7
MD5 422482e379e0c9b81dca92fa1b014765
BLAKE2b-256 6e4ce6578b6957d4c8cd41b2f0ec1e6b1b1c260ce2d54afb1aefe262c05e2d89

See more details on using hashes here.

Provenance

The following attestation bundles were made for omnime-0.2.8.tar.gz:

Publisher: publish.yaml on opalacoderdev/OmniMe

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file omnime-0.2.8-py3-none-any.whl.

File metadata

  • Download URL: omnime-0.2.8-py3-none-any.whl
  • Upload date:
  • Size: 3.7 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for omnime-0.2.8-py3-none-any.whl
Algorithm Hash digest
SHA256 5dc7c4fba299a3bf9133896b226c16720b49196c102f2bcfb8b522e2ccaaf991
MD5 124734489b0d2cd94604489dae6ed5e2
BLAKE2b-256 bdbdba5672b371194ac97ba6478af791db238001ffa148535f520d5bb8462d95

See more details on using hashes here.

Provenance

The following attestation bundles were made for omnime-0.2.8-py3-none-any.whl:

Publisher: publish.yaml on opalacoderdev/OmniMe

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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