Skip to main content

Omega

Omega is a personal agent that lives on your machine and keeps working with you across sessions. It maintains persistent conversations so you can pick up where you left off, a personal memory layer for durable facts about you and your work, and a knowledge base for documents, URLs, and code you want it to be able to search and reference later.

You choose the LLM provider. Omega keeps its database and local memory on your machine.

Install

Requirements:

  • Python 3.11+
  • Docker with Docker Compose running
  • An API key for Openrouter, Anthropic, or an OpenAI-compatible provider
pip install omega-agent
omega setup

omega setup starts Omega's bundled database, prepares its schema, asks for your LLM provider settings, verifies the connection, and checks the local embedding model.

Start chatting

omega --help

That lists all the omega commands.

omega

That opens Omega's full-screen terminal interface.

Use the simpler scrolling chat instead:

omega --cli

Resume your most recent conversation:

omega --continue

Start a clean session:

omega new

Inside Omega TUI, type /commands to see the available chat commands. /quit exits.

What Omega keeps

Omega has three seperate kinds of context:

  • Conversation history: your saved chat sessions.
  • Personal memory: durable facts you directly share, such as preferences or ongoing work
  • Knowledge base: URLs, notes, and code you deliberately add for later reference.

Add knowledge

omega ingest url "https://example.com/article"
omega ingest text "Notes I want Omega to search later"
omega ingest code --file ./main.py

Check queued or processed material:

omega kb list
omega kb status <item-id>

Check omega's installation

omega doctor

This checks the bundled database, pgvector, embedding model, provider configuration, and local memory directory.

Privacy

Omega stores its database and memory locally. Requests sent to an LLM go to the provider you configure. Those may include your chats, memory, knowledge base items. Your API key stays in your local configuration and is not in printed in Omega's normal output.

Download files

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

Source Distribution

omega_agent-0.1.0.tar.gz (71.3 kB view details)

Uploaded Source

Built Distribution

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

omega_agent-0.1.0-py3-none-any.whl (88.9 kB view details)

Uploaded Python 3

File details

Details for the file omega_agent-0.1.0.tar.gz.

File metadata

  • Download URL: omega_agent-0.1.0.tar.gz
  • Upload date:
  • Size: 71.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Fedora Linux","version":"43","id":"","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for omega_agent-0.1.0.tar.gz
Algorithm Hash digest
SHA256 dccf44922bf197793d9093277c29b616e7a11235fc5b1be89b61a1a6e9ca8ab8
MD5 136438326a7c80ecbcc93ab132a4d068
BLAKE2b-256 d2bf7d750b696d31c9058c8808367f1005760bc5c62072dade3608beecf8166f

See more details on using hashes here.

File details

Details for the file omega_agent-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: omega_agent-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 88.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Fedora Linux","version":"43","id":"","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for omega_agent-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5717c3f45cfbd9082169c63f12f6b2307f3032f433f6e61ee252364ddec6cc2c
MD5 0d9a6d965f10446a7316ee433069ccd9
BLAKE2b-256 655711509563c05fa937b8a13acf89202d82ec0435b482759179da05a1c06197

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 Sentry Error logging StatusPage Status page