Skip to content
NarraNexus
Multi-Agent Product · Open Source

An agent team,
ready in one click.

NarraNexus isn’t another framework for wiring agents together. It’s a ready-to-run team of agents that already remember, collaborate, and use tools. Start from a template, or compose your own.

Try OnlineDownload for macOSGet StartedGitHub

The cloud version is invite-only while we scale up. Request an invite code, or run the desktop / local version with no invite needed.

Get started

A working agent team in three steps.

No config sprawl. No bespoke wiring. Pick a surface, drop in a template, start the conversation.

Step 01

Set it up

Open the cloud app, install the macOS build, or run it locally from source. Pick the surface that fits. Your team is ready in minutes.

WEB · DESKTOP · LOCAL
Step 02

Browse a template

Pick a ready-made agent team: a research desk, a content studio, a briefing bot. Or start blank and shape your own.

TEMPLATES
Step 03

Import & start talking

One click to import. Your agents are online, share memory, and use tools out of the box. No wiring, no glue code.

ZERO CONFIG
Built for

Three places to start.

Three starting points. Concept-level for now. Drop in a template and the team is live.

Your AI research team

Daily morning briefings, market scans, deep dives. Agents that hold context across weeks of research instead of starting from scratch.

Your content studio

From idea to script to draft. Writers, editors, and producers that hand off cleanly. They remember what shipped last week.

A warm friend

Someone who remembers what you told them last Tuesday. A companion that picks up where you left off, in your tone of voice.

In practice

Your agent, at work.

The Financial Morning Briefing template mid-flow. Briefing Maestro coordinates five analysts behind the scenes, then delivers the day’s brief in your language, while you make coffee.

NarraNexusagent.narra.nexus
Interactionagent_e2ace957a084Ready
ME
give today’s briefing
11:25
BM
Briefing ready. Five analysts agreed on a macro-driven open. Deep-read below.
View reasoning & tools
briefing_2026-05-28.html
Artifact · 8.2 KB · HTML
11:26
Type your message…give today’s briefing
Briefing MaestroFinancial Morning Briefing · 金融晨报Cloud
Capabilities

What every agent comes with.

No wiring, no extensions. Four things your agent already has, the moment you import it.

Narrative Memory

Remembers the whole story, not just the last chapter

Topics become persistent storylines that carry their own history and active modules. New messages route to the right thread automatically. New subjects open a fresh one.

Learn more
Team Collaboration

Brings its own team to the job

Spin up a research desk, a content team, or an on-call rotation. Agents coordinate over a shared message bus: DM, group chat, hand-offs, and shared context across the whole team.

Learn more
Jobs & Long Tasks

Works while you sleep

Schedule one-offs, cron jobs, or always-on daemons. Agents work in the background and report back through chat when the results are ready.

Learn more
Social Network

Builds its own circle of contacts and fans

Every person, team, and agent it meets joins a graph your agent maintains: roles, expertise, communication style, history. It adapts who it talks to and how, based on who's asking.

Learn more
FAQ

Common questions

Is there a free tier?
Yes. New cloud accounts get a system-provided token quota covering Agent inference, embeddings, and helper calls. Enough to try the product end-to-end before you bring your own keys.
Can I bring my own model or API key?
Yes. NarraNexus runs on a three-slot architecture: Agent, Embedding, and Helper. You can plug in NetMind.AI Power (covers all three), OpenRouter, Yunwu, or any custom Anthropic / OpenAI-compatible endpoint.
Do my chats stay private?
Yes. Every agent is private by default: only you see its conversations. You can flip an agent public so others can discover and talk to it, but their chats stay isolated from yours.
Will my agent remember things between sessions?
Short-term memory in the active conversation is handled by the Chat module. Cross-session long-term memory lives in Narrative. Your agent picks up the right thread even weeks later, organized by topic rather than timestamp.
Can I run it fully locally?
Yes. The macOS desktop app ships with a bundled runtime and runs entirely on your machine: no account, no network round-trip. From source, one bash run.sh starts the full stack.
Multi-device login?
Supported. JWT tokens are per-device, so you can stay signed in on laptop, desktop, and phone in parallel. Agent narratives live server-side and stay in sync across them.

Full beginner guide and FAQ →

Roadmap

Where we are going

  1. 2026-03
    v1.0FoundationShipped
    • Core agent runtime with 7-step pipeline
    • Narrative memory engine
    • Module system with hot-pluggable capabilities
    • Built-in MCP tools
    • Multi-LLM provider support
  2. 2026-03
    v1.0.5Desktop & CloudShipped
    • macOS desktop app with bundled runtime
    • Cloud deployment with multi-tenant auth
    • Agent-to-agent communication (DM & group chat)
    • Skill system & ClawHub marketplace integration
    • Dashboard v2 with job tracking & cost monitoring
  3. 2026 Q2
    v2.0Scale & Integrate
    • Docker Compose one-command deployment
    • IM platform integrations (Telegram, Lark)
    • Community plugin system
    • Multimodal interaction support
Tonight

Talk to your first agent tonight.

Sixty seconds from open to your first reply.

Try OnlineOr download for macOS

Cloud is invite-only while we scale up. Request a code.