Privacy-first, self-evolving AI agent with GraphRAG memory, auto skill generation, plugin ecosystem, and web dashboard. 100% local. Zero config.
0
Core Modules
0
+ Test Cases
0
CLI Commands
0
% Open Source
Everything you need for a powerful, local AI agent that learns and evolves.
Persistent knowledge graph using NetworkX for intelligent context retrieval across sessions.
The agent writes its own tools during runtime and saves them permanently for reuse.
Extend with custom plugins, hot-reload support, and a hook-based architecture.
Optional FastAPI dashboard for monitoring skills, memory graph stats, and task history.
Local-first execution. Data stays on your machine when using Ollama. Your code, your rules.
Isolated skill execution with subprocess isolation, timeouts, and memory limits.
Export skills, graphs, and reports as JSON, Markdown, or shareable skill packs.
Check for new versions, auto-update skills from a central registry.
Works with any model via LiteLLM — Ollama, OpenAI, Anthropic, and more.
Install via pip, pull an Ollama model, and run your first task. Zero configuration needed.
The agent processes your prompt using GraphRAG memory for context-aware responses.
When the agent needs a tool it doesn't have, it writes one, tests it, and saves it permanently.
With each interaction, the knowledge graph grows and the skill tree expands. Your agent gets smarter.
$ 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 ✅
Based on publicly available documentation as of April 2026. Please verify for your use case.
| Feature | NexusAgent | Aider | Continue.dev | Cursor | OpenHands |
|---|---|---|---|---|---|
| Runs Locally (with Ollama) | ✅ | ✅ | ✅ | ❌ | ❌ |
| GraphRAG Memory | ✅ | ❌ | ❌ | ❌ | ❌ |
| Self-Evolving Skills | ✅ | ❌ | ❌ | ❌ | ❌ |
| Plugin System | ✅ | ❌ | ✅ | ✅ | ✅ |
| Zero-Config Setup | ✅ | ⚠️ | ⚠️ | ✅ | ⚠️ |
| CLI Interface | ✅ | ✅ | ❌ | ❌ | ❌ |
| Sandboxed Execution | ✅ | ❌ | ❌ | ❌ | ✅ |
| Open Source | MIT | Apache | Apache | Proprietary | MIT |
No telemetry, no tracking, no data leaves your machine. Your code stays yours.
The more you use it, the more capable it becomes. Skills accumulate over time.
MIT licensed with a plugin system. Modify, extend, and share freely.
GraphRAG memory (NetworkX), auto skill generation, CLI (run, evolve, status, skills), LiteLLM + Ollama
Config management (YAML/JSON), plugin system with hot-reload, FastAPI dashboard, sandboxed execution, export (JSON/Markdown/ZIP), self-updater, Docker, CI/CD, 30+ tests
Orchestration engine, task delegation & routing, collaborative shared memory, agent communication protocol, roles (coder/reviewer/tester/planner), priority queue
Voice interface (Whisper STT + TTS), IDE integration (JSON-RPC, VS Code), AST-aware code memory, context window management
Encrypted cloud sync, audit logging & RBAC, skill marketplace, performance benchmarks, mobile companion API
Everything you need to get the most out of NexusAgent.
Get started with NexusAgent in under 2 minutes.
pip install nexus-agent