Fishjam Js Server Sdk logo

Fishjam Js Server Sdk

Organization
software-mansion-labs
fishjam-js-server-sdk

Node.js / TypeScript server SDK for Fishjam — backends that create rooms, mint peer tokens, listen to server notifications, and run agents. Use when writing a Node.js / Express / Fastify / Hono / NestJS backend that talks to Fishjam, sets up a webhook receiver, runs an AI agent, generates livestream tokens, or composes streams. Trigger on: '@fishjam-cloud/js-server-sdk', 'FishjamClient', 'FishjamWSNotifier', 'FishjamAgent', 'createPeer', 'createRoom', 'createAgent', 'createVapiAgent', 'createLivestreamStreamerToken', 'createLivestreamViewerToken', 'refreshPeerToken', 'subscribeTracks', 'subscribePeer', 'createMoqToken', 'ServerMessage', 'roomCreated', 'peerAdded', 'trackAdded', 'fishjam backend Node', 'express fishjam', 'fastify fishjam', 'gemini agent fishjam', 'vapi fishjam', 'CompositionClient', 'createComposition', 'forwardRoomTracks'. Covers REST, WebSocket notifier, webhook protobuf decoding, FishjamAgent, Gemini Live integration, and CompositionClient.

Overview

Publishersoftware-mansion-labs
Repositoryskills
Skill namefishjam-js-server-sdk
Stars
296
Forks
21
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by software-mansion-labs on GitHub. Read the source before you install it.

Installation

Install the Fishjam Js Server Sdk AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/software-mansion-labs/skills/tree/main/skills/fishjam/references/js-server-sdk
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/software-mansion-labs/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/fishjam/references/js-server-sdk .claude/skills/fishjam-js-server-sdk
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fishjam Js Server Sdk in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Fishjam Js Server Sdk on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Fishjam Js Server Sdk is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Fishjam JS Server SDK

@fishjam-cloud/js-server-sdk — server-side Node.js / TypeScript SDK for the Fishjam platform.

Read ../platform/SKILL.md first. It defines rooms, peers, tracks, management tokens, peer tokens, and the WS-vs-webhook tradeoff that this skill builds on.

Four components

ComponentWhat it doesReference
FishjamClientREST client — rooms, peers, agents, livestream/MoQ tokens, subscribe modes.client.md
FishjamWSNotifierSubscribes to all 18 server events over a single WebSocket. Best for long-lived workers.ws-notifier.md
FishjamAgentProgrammatic peer — sends/receives audio frames over a server-side WS. Used for AI agents (Gemini, custom).agent.md
CompositionClientCompositions: register inputs and outputs, deploy templates, send events. Concepts in ../composition/SKILL.md.composition.md

Webhook receivers are not a class — you decode ServerMessage protobuf yourself; covered in webhooks.md.

Install + minimal flow

bash
npm install @fishjam-cloud/js-server-sdk
# or yarn add @fishjam-cloud/js-server-sdk
ts
import { FishjamClient } from '@fishjam-cloud/js-server-sdk';

const fishjamClient = new FishjamClient({
  fishjamId: process.env.FISHJAM_ID!,
  managementToken: process.env.FISHJAM_MANAGEMENT_TOKEN!,
});

const room = await fishjamClient.createRoom();
const { peer, peerToken } = await fishjamClient.createPeer(room.id, {
  metadata: { userId: 'user-123' },
});
// ship `peerToken` to your client

When to read which reference

TaskReference
Call any REST method (rooms, peers, subscribe, refresh)client.md
Subscribe to server events from a long-lived workerws-notifier.md
Receive events from a serverless / scaled-out backendwebhooks.md
Build an AI voice agent (audio in/out, image capture)agent.md
Wire a Gemini Live agent into a roomgemini-integration.md
Wire all of this into Express or Fastifyexpress-fastify.md
Issue livestream streamer/viewer tokens or MoQ tokenslivestream-and-moq.md
Use manual subscribe mode (cost / privacy / staging)selective-subscriptions.md
Compose streams: CompositionClient calls, forwarding a roomcomposition.md

Key rules

  • One FishjamClient per process. It's a thin axios wrapper — share, don't recreate per request.
  • Catch SDK exceptions, not axios errors. All methods wrap REST calls in mapException, throwing typed errors (BadRequestException 400, UnauthorizedException 401, RoomNotFoundException / PeerNotFoundException / FishjamNotFoundException 404, ServiceUnavailableException 503, UnknownException for anything else — including 403). All inherit from FishjamBaseException, which is useful for a catch-all instanceof branch. ForbiddenException is exported but never produced by the current mapper. Match on these to map to HTTP status codes. Constructor also throws MissingFishjamIdException synchronously if fishjamId is falsy.
  • Management token stays in the backend. Never put it in NEXT_PUBLIC_*, VITE_*, or any bundled env. If exposed, regenerate from the Dashboard.
  • Deprecation header. The client logs x-fishjam-api-deprecated once per process. If you see it, plan a migration — don't silence it.
  • FishjamWSNotifier does NOT auto-reconnect. The constructor opens one WS; if it closes, you must reinstantiate. Wrap it in a supervisor or use webhooks instead.
  • Peer tokens are valid for 24 hours from creation. The token is consumed during the initial WS handshake; an established session keeps running on its own and isn't dropped when the token's wall-clock expiry passes. If the peer hasn't connected yet, or needs to reconnect after the 24h window, call refreshPeerToken to mint a new one and ship it to the client.

References

FileWhen to read
client.mdThe REST surface — every method on FishjamClient with signatures and examples.
ws-notifier.mdFishjamWSNotifier wiring, the 18 events, reconnection patterns.
webhooks.mdDecoding application/x-protobuf webhook bodies with ServerMessage.decode.
agent.mdFishjamAgent — opus/pcm16, createTrack, sendData, captureImage, interruptTrack.
gemini-integration.md@fishjam-cloud/js-server-sdk/gemini — createClient, audio settings, end-to-end demo.
express-fastify.mdProduction wiring — /api/join-room, error mapping, webhook routes, Fastify plugin.
livestream-and-moq.mdcreateLivestreamStreamerToken, createLivestreamViewerToken, createMoqToken.
selective-subscriptions.mdsubscribePeer / subscribeTracks with peers created using subscribeMode: 'manual'.
composition.mdCompositionClient: compositions, inputs, outputs, templates, events, exceptions.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Fishjam Js Server Sdk AI skill do?

Node.js / TypeScript server SDK for Fishjam — backends that create rooms, mint peer tokens, listen to server notifications, and run agents. Use when writing a Node.js / Express / Fastify / Hono / NestJS backend that talks to Fishjam, sets up a webhook receiver, runs an AI agent, generates livestream tokens, or composes streams. Trigger on: '@fishjam-cloud/js-server-sdk', 'FishjamClient', 'FishjamWSNotifier', 'FishjamAgent', 'createPeer', 'createRoom', 'createAgent', 'createVapiAgent', 'createLivestreamStreamerToken', 'createLivestreamViewerToken', 'refreshPeerToken', 'subscribeTracks', 'sub...

Why use Fishjam Js Server Sdk on TypingMind?

Because you install it once and use it with any model. Fishjam Js Server Sdk is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Fishjam Js Server Sdk in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/software-mansion-labs/skills/tree/main/skills/fishjam/references/js-server-sdk. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Fishjam Js Server Sdk?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Fishjam Js Server Sdk?

As many as you like. As long as a model supports skills, you can use Fishjam Js Server Sdk with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Fishjam Js Server Sdk AI skill free?

Yes. It is published on GitHub by software-mansion-labs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇