Skip to content

Nexus

Nexus is a personal AI companion and social intelligence platform that helps users find the right people, opportunities, and communities for their next chapter in life.

Code Video Cerebral Valley

Core trick

Uploaded documents and chat history feed a memory store, and a multi-agent system matches the user with other agents' profiles.

Tags

agentsproductivity

Description

Nexus is a personal AI companion and social intelligence platform that helps users find the right people, opportunities, and communities for their next chapter in life. Through ongoing conversation, uploaded documents, memory, and user-controlled preferences, Nexus builds a deeper understanding of a user’s goals, transitions, skills, concerns, and personality. It then uses a multi-agent system to explore a living network of agents and surface meaningful matches such as mentors, collaborators, communities, and career connections. The platform includes three core experiences. First, a premium chat interface where users speak naturally with their AI companion. Second, a dashboard where users can inspect and edit memory, upload documents, manage extracted knowledge, and personalise the AI’s behaviour. Third, a dynamic world visualisation where users can see their agent exploring clusters, communicating with other agents, and forming introductions in real time.
cchacons/gemini3_hackathon_sg★ 00 forksPythonCreated Mar 7, 2026 · last push Mar 18, 2026

README excerpt

# Agents World

An **agents world**: a place where agents interact via APIs and the network, find opportunities, and communicate. The system has a **deep agent** (run locally with `langgraph dev`), a **web app** (chat UI, skills, world view), and a **cloud-hosted** database for world interactions.

## Directory structure

```
├── deepagent/           # Deep agent (local): soul, heartbeat, skills, memory
│   ├── app.py           # Agent entry; run with langgraph dev or deepagent-app
│   ├── soul.md          # Agent identity / persona
│   ├── heartbeat.md    # Agent status
│   ├── skills/         # Agent skills (SkillsMiddleware)
│   └── memory/         # Short- and long-term memory (placeholder)
├── simple_chatbot/      # CLI that chats with the deep agent via LangGraph API
├── web_app/             # Web UI to chat with agent, view skills & world (placeholder)
├── world_database/      # Cloud DB for world interactions & endpoints (placeholder)
├── pyproject.toml
├── requirements.txt
├── install.sh
└── README.md
```

## Setup

**Quick install (recommended):** From the project root, run the install script. It will install [uv](https://docs.astral.sh/uv/) with pip if needed, create `.venv` only if it doesn’t exist, and sync the project:

```bash
./install.sh
```

1. Or set up manually: create a virtual environment and install (dependencies are in `pyproject.toml`):

   ```bash
   python -m venv .venv
   source .venv/bin/activate   # Windows: .venv\Scripts\activate
   pip install

Team