Skip to content

Nexus

AI-Native Filesystem for Building Intelligent Agents

Store files. Remember context. Control access. Scale instantly.

Give your AI agents a filesystem that thinksβ€”with memory, permissions, and learning built in.

⚑ What is Nexus? (10-second pitch)

Nexus is a programmable filesystem for AI agents that combines:

  • πŸ“ File Storage - Store and version files (local, S3, GCS)
  • 🧠 Agent Memory - Agents remember and learn across sessions
  • πŸ”’ Smart Permissions - Fine-grained access control (ReBAC/Zanzibar-style)
  • πŸ” Semantic Search - Find anything with natural language
  • πŸš€ Zeroβ†’Production - Start local (pip install), scale without code changes

One API. Multiple backends. Built for AI agents.

Quick Start in 30 Seconds

# Install
pip install nexus-ai-fs

# Use it
import nexus

# Just works - no auth needed in embedded mode
nx = nexus.connect(config={"data_dir": "./nexus-data"})

# Write and read files
nx.write("/hello.txt", b"Hello, Nexus!")
content = nx.read("/hello.txt")
print(content.decode())  # "Hello, Nexus!"
# Install
pip install nexus-ai-fs

# Initialize workspace
nexus init ./my-project

# Use with server (see Server Mode tab)
export NEXUS_URL=http://localhost:2026
export NEXUS_API_KEY=your-key
nexus write /workspace/hello.txt "Hello from CLI!"
nexus cat /workspace/hello.txt
# Start server with authentication
nexus serve --host 0.0.0.0 --port 2026

# Connect from Python
import nexus
nx = nexus.connect(
    remote_url="http://localhost:2026",
    api_key="your-api-key"
)
nx.write("/workspace/hello.txt", b"Remote write!")

πŸ‘‰ Learn more: Administration & Operations (25 min)

🎯 Is Nexus For Me?

Answer 2 quick questions to find your path:

1. What are you building?

Perfect fit! Nexus is built specifically for AI agents.

βœ… You need: Agent memory, persistent storage, multi-agent collaboration πŸ‘‰ Start here: AI Agent Memory (15 min)

Use cases: - Multi-agent teams (CrewAI, LangGraph workflows) - Chatbots with long-term memory across sessions - Code assistants that learn from your codebase - Research agents that build knowledge over time

Frameworks supported: CrewAI, LangGraph, Claude SDK, OpenAI Agents, Google ADK

Excellent choice! LLM-powered reading and semantic search built-in.

βœ… You need: Document search, AI-powered Q&A, content processing πŸ‘‰ Start here: Document Q&A System (10 min)

Use cases: - Knowledge bases with natural language search - Document processing pipelines with batch uploads - Content analysis with LLM-powered insights - RAG systems with semantic search

Great choice! Built-in multi-tenancy and fine-grained permissions.

βœ… You need: Workspace isolation, ReBAC permissions, audit trails πŸ‘‰ Start here: Multi-Tenant SaaS (30 min)

Use cases: - Collaboration platforms with team workspaces - Enterprise apps with tenant isolation - Data platforms with row-level access control - AI-powered SaaS with agent workspace sharing

Perfect! Event-driven workflows and plugin extensibility.

βœ… You need: Automated pipelines, custom integrations, event triggers πŸ‘‰ Start here: Workflow Automation (15 min)

Use cases: - Data pipelines with automatic processing - File-based triggers (e.g., invoice β†’ extract β†’ store) - Custom integrations via plugin system - ML experiment tracking with versioned checkpoints

Excellent! Package and share AI capabilities as reusable skills.

βœ… You need: Skill discovery, documentation-to-skill conversion, team sharing πŸ‘‰ Start here: Skills Management (20 min)

Use cases: - Team skill libraries from internal/external documentation - Auto-generate skills from any docs URL - Skill discovery across agent/tenant/system tiers - Knowledge sharing with ReBAC permissions - AI agent enhancement with contextual skills

2. What's your experience level?

Recommended Path:

  1. Quick Start (30 sec) - Copy-paste working code
  2. Core Concepts (5 min) - Understand the mental model
  3. Choose Your Learning Path - Pick based on use case

πŸ’‘ Tip: Start with embedded mode, switch to server later (same code!)

Advanced guides:


Still not sure? Check out Why Nexus? for detailed comparisons with S3, Vector DBs, and traditional filesystems.

How It Works

%%{init: {'theme':'base', 'themeVariables': { 'primaryColor':'#e3f2fd','primaryTextColor':'#1a237e','primaryBorderColor':'#5C6BC0','lineColor':'#AB47BC','secondaryColor':'#fce4ec','tertiaryColor':'#fff3e0','fontSize':'14px'}}}%%
graph TB
    subgraph agents[" πŸ€– AI Agents "]
        agent1["Agent A<br/>(GPT-4)"]
        agent2["Agent B<br/>(Claude)"]
        agent3["Agent C<br/>(Custom)"]
    end

    subgraph vfs[" πŸ“ Nexus Virtual File System "]
        api["Unified VFS API<br/>read() write() list() search()"]
        memory["πŸ’Ύ Memory API<br/>Persistent learning & context"]
        rebac["πŸ”’ ReBAC Permissions<br/>Backend-aware object types"]
        version["πŸ“¦ Versioning<br/>Snapshots & time-travel"]
        router["Smart Router<br/>Path β†’ Backend + Object Type"]
    end

    subgraph backends[" πŸ’Ύ Storage & Data Backends "]
        subgraph storage[" File Storage "]
            local["Local Filesystem<br/>object: file"]
            gcs["Cloud Storage<br/>object: file"]
        end
        subgraph data[" Data Sources "]
            postgres["PostgreSQL<br/>object: postgres:table/row"]
            redis["Redis<br/>object: redis:instance/key"]
            mongo["MongoDB<br/>object: mongo:collection/doc"]
        end
    end

    agent1 -.->|"write('/workspace/data.json')"| api
    agent2 -.->|"read('/db/public/users')"| api
    agent3 -.->|"memory.store('learned_fact')"| memory

    api --> rebac
    memory --> rebac
    rebac <-->|"Check with object type"| router
    rebac -->|"βœ“ Allowed"| version
    version --> router

    router -->|"File operations"| local
    router -->|"File operations"| gcs
    router -->|"Queries as files"| postgres
    router -->|"KV as files"| redis
    router -->|"Documents as files"| mongo

    style agents fill:#e3f2fd,stroke:#5C6BC0,stroke-width:2px,color:#1a237e
    style vfs fill:#f3e5f5,stroke:#AB47BC,stroke-width:2px,color:#4a148c
    style backends fill:#fff3e0,stroke:#FF7043,stroke-width:2px,color:#e65100
    style storage fill:#e8f5e9,stroke:#4CAF50,stroke-width:1px
    style data fill:#e1f5fe,stroke:#0288D1,stroke-width:1px
    style api fill:#5C6BC0,stroke:#3949AB,stroke-width:2px,color:#fff
    style memory fill:#AB47BC,stroke:#7B1FA2,stroke-width:2px,color:#fff
    style rebac fill:#EC407A,stroke:#C2185B,stroke-width:2px,color:#fff
    style version fill:#66BB6A,stroke:#388E3C,stroke-width:2px,color:#fff
    style router fill:#42A5F5,stroke:#1976D2,stroke-width:2px,color:#fff

Backend Abstraction:

Nexus presents everything as files to users, while backends provide appropriate object types for permission control:

  • File Storage (Local, GCS, S3): Standard file objects
  • Databases (PostgreSQL, Redis, MongoDB): Backend-specific objects (tables, keys, documents)
  • Unified Interface: All accessed through the same VFS API (read/write/list)
  • Fine-Grained Permissions: ReBAC uses backend-appropriate object types (e.g., grant access to a PostgreSQL schema vs. individual rows)

🎯 One API

Agents use simple file operations, regardless of where data lives. No cloud SDKs to learn.

πŸ”’ Built-in Security

Every operation checks permissions automatically. Google Zanzibar-style ReBAC included.

πŸ’Ύ Agent Memory

Persistent learning across sessions. Agents remember context and improve automatically.

πŸ“¦ Versioning

Time-travel debugging with snapshots. Roll back to any point in history instantly.

πŸ”„ Backend Flexibility

Switch from local to cloud without changing agent code. Zero vendor lock-in.

πŸš€ Production Ready

Multi-tenancy, workspace isolation, and complete audit trails out of the box.

⚑ Workflow Automation

Event-driven workflows fire automatically on file operations. No manual triggering needed.

🧠 Core Concepts

New to Nexus? Start here to understand how it works:

  • What is Nexus?


    Mental model and architecture overview. Understand the three-layer system and key design principles.

    Read Concept

  • Memory System


    How agents remember context across sessions. Learn about namespaces, identity-based memory, and persistence.

    Read Concept

  • Agent Permissions


    How agents authenticate and inherit permissions from users. ReBAC for multi-agent collaboration.

    Read Concept

  • ReBAC Explained


    Deep dive into Relationship-Based Access Control. Zanzibar-style permissions with tuples and expansion.

    Read Concept

  • Content-Addressable Storage


    How CAS works with SHA-256 hashing. Automatic deduplication and immutable version history.

    Read Concept

  • Learning Loops


    Algorithm-agnostic learning primitives. Trajectories, reflection, playbooks, and feedback collection.

    Read Concept

  • Workflows & Triggers


    Event-driven automation with file patterns. Auto-process documents, validate data, and send webhooks.

    Read Concept

πŸŽ“ Choose Your Learning Path

Progressive learning from beginner to advanced. Pick based on your use case and experience level.

🌱 Beginner Paths (5-15 minutes)

  • πŸ“ Simple File Storage


    Master basic read/write operations with local and cloud backends.

    ⏱️ 5 min | πŸ’‘ Difficulty: Easy

    Start Learning

  • πŸ” Document Q&A System


    Build semantic search and LLM-powered document reading.

    ⏱️ 10 min | πŸ’‘ Difficulty: Easy

    Start Learning

  • 🧠 AI Agent Memory


    Add persistent memory and learning to your agents.

    ⏱️ 15 min | πŸ’‘ Difficulty: Medium

    Start Learning

  • πŸ”„ Workflow Automation


    Build event-driven workflows that trigger automatically.

    ⏱️ 15 min | πŸ’‘ Difficulty: Medium

    Start Learning

πŸš€ Intermediate Paths (15-25 minutes)

  • πŸ‘₯ Team Collaboration


    Multi-user access with permissions and workspace isolation.

    ⏱️ 20 min | πŸ’‘ Difficulty: Medium

    Start Learning

  • πŸ€– Agent Framework Integration


    Connect LangGraph, CrewAI, Claude SDK, and OpenAI Agents.

    ⏱️ 20 min | πŸ’‘ Difficulty: Medium

    Start Learning

  • πŸ’Ύ Multi-Backend Storage


    Mount and federate S3, GCS, and database backends.

    ⏱️ 20 min | πŸ’‘ Difficulty: Medium

    Start Learning

  • 🧠 Agent Memory & Learning


    Build agents that learn and improve over time.

    ⏱️ 20 min | πŸ’‘ Difficulty: Medium

    Start Learning

βš™οΈ Advanced Paths (25-30+ minutes)

  • 🏒 Multi-Tenant SaaS


    Build production SaaS with complete tenant isolation.

    ⏱️ 30 min | πŸ’‘ Difficulty: Hard

    Start Learning

  • ⚑ Skills Management


    Create, version, and publish reusable agent skills.

    ⏱️ 15 min | πŸ’‘ Difficulty: Medium

    Start Learning

  • πŸ”§ Administration & Operations πŸ†•


    User management, API keys, monitoring, and backup.

    ⏱️ 25 min | πŸ’‘ Difficulty: Hard | πŸ“‘ Server Mode

    Start Learning

  • πŸ”Œ Building Plugins πŸ†•


    Extend Nexus with custom functionality and lifecycle hooks.

    ⏱️ 30 min | πŸ’‘ Difficulty: Hard

    Start Learning

Not sure where to start? Use the Is Nexus For Me? quiz above to find your recommended path.

What Makes Nexus Different?

For AI Agent Developers

Feature Vector DB (Pinecone) Object Storage (S3) Traditional FS Nexus
Agent Memory 🟑 Embeddings only ❌ ❌ βœ… Memory + Learning
File Operations ❌ 🟑 Object-only βœ… βœ… Full POSIX-like API
Semantic Search βœ… ❌ ❌ βœ… Vector + metadata
Multi-Agent Collaboration ❌ ❌ ❌ βœ… Shared workspaces
Permissions & ReBAC 🟑 Basic 🟑 IAM policies 🟑 UNIX perms βœ… Zanzibar-style ReBAC
Multi-Tenancy 🟑 Collections 🟑 Manual buckets ❌ βœ… Native isolation
Event-Driven Workflows ❌ 🟑 S3 notifications ❌ βœ… Auto-trigger on writes
Time Travel & Versioning ❌ 🟑 Versioning only ❌ βœ… Full history + diffs
Database Access as Files ❌ ❌ ❌ βœ… PostgreSQL, Redis, MongoDB
LLM Document Reading ❌ ❌ ❌ βœ… Query docs with citations

Why AI Developers Choose Nexus:

  • πŸ€– Multi-Agent Native: Built-in workspace sharing and collaboration for CrewAI, LangGraph teams
  • 🧠 Memory + Storage Combined: Not just embeddingsβ€”full agent memory with automatic consolidation
  • πŸ”„ Event-Driven Automation: Workflows trigger automatically when agents write files (no manual event firing)
  • πŸ—„οΈ Unified Data Access: Access files, databases (PostgreSQL/Redis/MongoDB), and vectors through one API
  • πŸ”’ Production-Ready Security: Fine-grained ReBAC permissions with multi-tenancy out of the box
  • πŸ“š LLM-Powered Intelligence: Ask questions about stored documents, get AI answers with citations
  • ⚑ Framework Integrations: First-class support for CrewAI, LangGraph, Claude SDK, OpenAI Agents, Google ADK

πŸ†˜ Need Help?

  • πŸ“– Quickstart Guide


    Step-by-step setup in under 10 minutes

    Get Started

  • πŸ”§ Troubleshooting


    Common issues and solutions

    Troubleshooting 101

  • πŸ’‘ Core Concepts


    Understand how Nexus works

    Learn Concepts

  • πŸ“š Glossary


    Complete A-Z reference: ReBAC, CAS, ACE, and all Nexus terminology

    View Glossary



**Ready to build?** Start with our [30-second quickstart](#quick-start-in-30-seconds) or [find your learning path](#-is-nexus-for-me). ⭐ **If Nexus helps your project, please [star us on GitHub](https://github.com/nexi-lab/nexus)!**