v1.0 — Production Release

The AI Agent That
Builds Its Own Tools

Privacy-first, self-evolving AI agent with GraphRAG memory, auto skill generation, plugin ecosystem, and web dashboard. 100% local. Zero config.

🛡️ Privacy-First ⚡ Zero Config 🔌 Extensible

0

Core Modules

0

+ Test Cases

0

CLI Commands

0

% Open Source

Packed with Features

Everything you need for a powerful, local AI agent that learns and evolves.

🧠

GraphRAG Memory

Persistent knowledge graph using NetworkX for intelligent context retrieval across sessions.

🔧

Auto Skill Generation

The agent writes its own tools during runtime and saves them permanently for reuse.

🔌

Plugin System

Extend with custom plugins, hot-reload support, and a hook-based architecture.

🌐

Web Dashboard

Optional FastAPI dashboard for monitoring skills, memory graph stats, and task history.

🔒

Privacy-First

Local-first execution. Data stays on your machine when using Ollama. Your code, your rules.

📦

Sandboxed Execution

Isolated skill execution with subprocess isolation, timeouts, and memory limits.

💾

Export System

Export skills, graphs, and reports as JSON, Markdown, or shareable skill packs.

🚀

Self-Updating

Check for new versions, auto-update skills from a central registry.

🎯

Multi-Model

Works with any model via LiteLLM — Ollama, OpenAI, Anthropic, and more.

How It Works

1

Install & Run

Install via pip, pull an Ollama model, and run your first task. Zero configuration needed.

2

Agent Processes & Remembers

The agent processes your prompt using GraphRAG memory for context-aware responses.

3

Skills Auto-Generate

When the agent needs a tool it doesn't have, it writes one, tests it, and saves it permanently.

4

Evolves Over Time

With each interaction, the knowledge graph grows and the skill tree expands. Your agent gets smarter.

Quick Start

terminal

$ pip install nexus-agent

$ ollama pull llama3

$ nexus run "Create a Python web scraper"

⚡ NexusAgent initialized. Model: ollama/llama3

🧠 Thinking and consulting GraphRAG memory...

Agent Response:

[NEW SKILL: web_scraper]

```python

import requests

from bs4 import BeautifulSoup

def scrape(url): ...

```

$ nexus skills

📋 Skill Tree: web_scraper ✅

Why NexusAgent?

Based on publicly available documentation as of April 2026. Please verify for your use case.

FeatureNexusAgentAiderContinue.devCursorOpenHands
Runs Locally (with Ollama)
GraphRAG Memory
Self-Evolving Skills
Plugin System
Zero-Config Setup⚠️⚠️⚠️
CLI Interface
Sandboxed Execution
Open SourceMITApacheApacheProprietaryMIT

Built on Principles

🔒

Privacy by Design

No telemetry, no tracking, no data leaves your machine. Your code stays yours.

🌱

Self-Improving

The more you use it, the more capable it becomes. Skills accumulate over time.

🔓

Open & Extensible

MIT licensed with a plugin system. Modify, extend, and share freely.

Roadmap

v0.1 — Core Agent

GraphRAG memory (NetworkX), auto skill generation, CLI (run, evolve, status, skills), LiteLLM + Ollama

v0.2 — Plugins & Dashboard

Config management (YAML/JSON), plugin system with hot-reload, FastAPI dashboard, sandboxed execution, export (JSON/Markdown/ZIP), self-updater, Docker, CI/CD, 30+ tests

v0.3 — Multi-Agent

Orchestration engine, task delegation & routing, collaborative shared memory, agent communication protocol, roles (coder/reviewer/tester/planner), priority queue

v0.4 — Voice & IDE

Voice interface (Whisper STT + TTS), IDE integration (JSON-RPC, VS Code), AST-aware code memory, context window management

v1.0 — Production

Encrypted cloud sync, audit logging & RBAC, skill marketplace, performance benchmarks, mobile companion API

FAQ

Is my data sent anywhere?+
By default, NexusAgent uses local Ollama models. If you configure cloud providers (OpenAI, Anthropic), prompts will be sent to those APIs. No additional telemetry or tracking is collected.
What models does it support?+
Any model supported by LiteLLM: Ollama (Llama, Mistral, CodeLlama, etc.), OpenAI (GPT-4), Anthropic (Claude), and more.
How does self-evolution work?+
When the agent encounters a task requiring a tool it doesn't have, it generates the tool code and saves it permanently to the skill tree. Future similar requests reuse the saved skill instead of regenerating code.
Can I use it without Ollama?+
Yes. Configure any LiteLLM-compatible provider via `nexus config set model.default openai/gpt-4`. You'll need an API key for cloud providers.
How do I write plugins?+
Create a Python file in `.nexus/plugins/` with functions named `nexus_*`. These become hooks that are called at various points in the agent lifecycle. See the plugin guide for details.

Documentation

Everything you need to get the most out of NexusAgent.

Ready to Build?

Get started with NexusAgent in under 2 minutes.

pip install nexus-agent