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 with every interaction.
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 with Ollama. Your data stays on your machine. Optional cloud models via LiteLLM.
Isolated skill execution with subprocess isolation, timeouts, and memory limits.
Orchestrate multiple agents with task delegation, role-based routing, and shared memory.
Encrypted cloud sync (Fernet), audit logging with RBAC, and structured JSON-lines logs.
Works with any model via LiteLLM — Ollama, OpenAI, Anthropic, Google, and more.
From zero to a self-evolving AI agent in minutes.
Install via pip, pull an Ollama model, and run your first task. No configuration files, no API keys, no setup wizards.
The agent processes your prompt using GraphRAG memory for context-aware responses. Every interaction enriches the knowledge graph.
When the agent needs a tool it doesn't have, it writes one and saves it permanently. Future requests reuse saved skills automatically.
With each interaction, the knowledge graph grows and the skill tree expands. Your agent gets smarter the more you use it.
A modular architecture designed for extensibility, privacy, and performance.
Based on publicly available documentation as of April 2026. 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 when using local models. Your code stays yours.
The more you use it, the more capable it becomes. Skills accumulate and the knowledge graph grows organically.
MIT licensed with a plugin system. Modify, extend, and share freely. No vendor lock-in.
GraphRAG memory (NetworkX), auto skill generation, CLI, LiteLLM + Ollama
Config management, plugin system with hot-reload, FastAPI dashboard, sandboxed execution, export, Docker, CI/CD
Orchestration engine, task delegation & routing, collaborative shared memory, agent roles, priority queue
Voice interface (Whisper STT + TTS), IDE integration (JSON-RPC), AST-aware code memory, context window management
Encrypted cloud sync, audit logging & RBAC, skill marketplace, performance benchmarks, mobile companion API, 140+ tests
nexus config set model.default <model>.nexus evolve command scans your workspace to enrich the knowledge graph.nexus config set model.default openai/gpt-4. You'll need an API key set as an environment variable for cloud providers..nexus/plugins/ with functions prefixed nexus_*. These hooks are called automatically at various points in the agent lifecycle. See the plugin guide for details.sys.executable for compatibility across platforms.Everything you need to get the most out of NexusAgent.
Get started with NexusAgent in under 2 minutes.
$ pip install nexus-agent