I am a ML/AI Engineer with 4+ years of experience. I specialize in building and deploying Agentic Systems to classified environments which leverage advance tools and customer databases (vector databases, object storage, postgres, mongo, elastic, kabana) to make sense of data and assist analysts with automating their workflows. On the side I build many ai applications, most of which are private repos.

Companion is an advanced AI agent system designed to assist with deep research, analysis, and report writing. It operates as a persistent companion that learns and stores information using a structured file system.

The purpose of Companion is to bridge the gap between the industry standard "Chat Bots" and the "Overkill Deep Researchers" that often acompany them.

Companion meets in the middle. Allowing a user to do deeper controlled research, whilst maintaining a collection of source information found. Companion offers the ability to spin up parallel or sequential agents to research and write.

Feel free to pull and help improve Companion. Currently it is fully written in python utilizing langchain and deepagents.

1. Utilize langchains create_agent and middleware instead of relying on create_deep_agents from deepagents
2. Pydantic Type and modularize the system to be more extensible
3. Improve CLI. I have mostly vibecoded the cli and would love to take it to the next level
4. Create a beautiful UI
5. Dockerize