Why Nexus?

Nexus is a project-centric memory and coordination platform for AI-assisted software development. It gives your AI agents a durable, structured knowledge base that persists across sessions — so architectural decisions, project context, and accumulated learnings are never lost in ephemeral chat windows.

Instead of relying on copy-paste feedback loops or rebuilding context from scratch in every conversation, Nexus provides a shared workspace where agents can read, write, and reason over project knowledge in a controlled, auditable way.

Nexus is built for development teams and solo developers who use AI agents — such as Claude, GPT, or GitHub Copilot — as part of their daily workflow. It is especially valuable for teams that work on longer-running projects where context management, reproducibility, and knowledge retention matter more than one-shot code generation.

Whether you are building features in legacy codebases, managing infrastructure with DevOps agents, or maintaining architectural standards across a growing team, Nexus ensures your agents work with the right context every time.

Nexus organizes project knowledge into structured entity types that reflect how real teams work:

• Architecture Decision Records (ADRs) — document and govern architectural choices with a full lifecycle: draft, review, accept, supersede.
• Sessions — execution history that captures what happened during a work session, including tasks created, decisions referenced, and letters exchanged.
• Vault Letters — asynchronous coordination between agents and humans with threading, acknowledgment, and audit trails.
• Research Notes & Documents — ingested project artifacts like PDFs, Markdown files, and screenshots that become searchable project context.

This approach ensures that durable learnings live in the project knowledge base — not in ephemeral chat sessions.

Nexus communicates with AI agents via the Model Context Protocol (MCP). Any MCP-compatible agent runtime can connect to the Nexus MCP server, which exposes 38 tools across knowledge access, coordination, governance, and review layers.

This means Nexus works with OpenCode, Claude Code, and any other tool that supports MCP — without being tied to a specific model or provider. The focus is on the quality of your project context, not on which model you use.

Skills are reusable, versioned agent instructions that you can manage centrally and assign to projects. Think of them as documented playbooks that tell agents how to approach specific tasks — from code review workflows to infrastructure scaffolding.

Skills go through a lifecycle: draft, review, and activation. They can be pinned to specific versions per project and are pulled into agent workspaces via the CLI. This ensures consistency and reproducibility across your team.

Nexus is designed with tenant isolation at its core. The platform is backed by Supabase with Row-Level Security (RLS) policies enforced at the database layer. Every query is scoped to your tenant, and project access is governed by a dual-layer RBAC model.

Sensitive project context stays within your tenant boundary. API tokens use SHA-256 hashing at rest, and the architecture supports self-hosted deployments for organizations that need full control over their data.

Nexus offers four tiers to match different team sizes and needs:

• Community (Free) — 1 seat, 3 projects, basic features. Great for individual exploration.
• Starter (49 EUR/year) — 1 seat, 5 projects, 3 customers. For solo developers getting started.
• Teams (149 EUR/year) — 10 seats, 50 projects, full skill lifecycle, ADR governance, vault letters, and audit logs.
• Enterprise (799 EUR/year) — Unlimited resources, SSO, custom branding, dedicated support, and full platform access.

Getting started with Nexus takes just a few steps:

1. Sign up and request a demo license.
2. Install the Nexus CLI and authenticate with nexus login.
3. Initialize a project workspace with nexus init.
4. Connect your MCP-compatible agent and start building project knowledge.

Yes. Nexus follows an open-core architecture and is designed to support self-hosted deployments. The platform runs on standard infrastructure — Next.js, Supabase (PostgreSQL), and optional S3-compatible storage — making it straightforward to deploy in your own environment or private cloud.

This is especially relevant for teams with strict data residency requirements or organizations that need full control over their AI agent infrastructure.

Nexus is actively evolving. Upcoming areas of focus include deeper document ingest capabilities (PDFs, screenshots, and structured artifacts), enhanced vector search for semantic project context, expanded CLI tooling, and tighter integration with additional agent runtimes.

For the full roadmap, visit the Roadmap page.