Cognipeer Developer Hub
Console
Studio
Agent Runtime

Developer hub for Console, Studio, and SDKs

Cognipeer Developers is the routing layer for teams building with Cognipeer. It clarifies which product fits which team and sends you to the right product and documentation.

Studio teams should begin with Client SDK. Platform teams should begin with Console and Console SDK. Custom runtime teams should move into Agent SDK, Agent Server, and Chat UI.

Start Here

Pick the right path first

Console Path

Self-hosted gateway, control plane, tracing, vectors, files, and typed platform integration.

Studio Path

Conversations, peers, channels, user context, and client-side tools inside your own app.

Runtime Path

Deterministic agents, serving infrastructure, and embeddable chat UI for custom stacks.

Each product keeps its own detailed documentation. This portal stays focused on product separation and entry guidance.

I am building on Cognipeer Console

Start here if you need the self-hosted gateway, multi-tenant control plane, OpenAI-compatible APIs, vectors, files, guardrails, and tracing.

  • Best for platform teams and backend integrators
  • Use Console SDK when your app talks to a Console deployment
  • Detailed platform documentation is available per product

I am integrating Cognipeer Studio into an app

Start here if your product needs Studio conversations, peers, channels, user context, or client-side tool execution inside your own frontend or backend.

  • Best for Studio-focused product teams
  • Use Client SDK for browser and Node integrations
  • Detailed Studio documentation is available per product

I am composing custom agent runtimes

Start here if you are assembling your own agent execution stack with deterministic runtime logic, serving APIs, and reusable chat components.

  • Use Agent SDK for runtime control
  • Use Agent Server to publish agents as APIs
  • Use Chat UI for embeddable conversational experiences
How The Stack Splits

Choose the right surface before you go deeper

This page is the routing layer that helps developers decide whether they belong in Console, Studio, or the composable agent runtime stack before they move into product-specific guides.

Console Platform

Infrastructure and integration surface for multi-tenant AI operations, external APIs, and typed application access.

Cognipeer Console

AI Gateway & Control Plane

Open

Cognipeer Console SDK

TypeScript SDK for Cognipeer Console

Open

Studio Integration

Application-facing SDK for teams that only need Studio-side conversational integration and client tool execution.

Cognipeer Client SDK

Studio Integration SDK

Open

Composable Runtime

Reusable building blocks for custom agent logic, serving, and user-facing interfaces outside the managed Studio flow.

Cognipeer Agent SDK

Deterministic TypeScript Agent Runtime

Open

Cognipeer Agent Server

Agent Serving Infrastructure

Open

Cognipeer Chat UI

AI Conversational Interface Kit

Open
SDK Decision

Client SDK vs Console SDK

These two SDKs serve different products. Mixing them in the wrong place creates confusion, so the developer site needs to call this out clearly.

Console SDK

Best-fit guidance

Choose this when your application connects to a Cognipeer Console deployment and needs chat, embeddings, vectors, files, tracing, or guardrails.

Client SDK

Best-fit guidance

Choose this when your application integrates Cognipeer Studio concepts such as conversations, peers, channels, hooks, and client-side tool execution.

Products

Explore the product summaries

Start with the product summary that matches your team. Each summary explains where the product fits, who it is for, and where to continue for implementation details.

Console Platform

Cognipeer Console

AI Gateway & Control Plane

Self-hosted AI infrastructure with OpenAI-compatible API, provider routing & resiliency, vector orchestration, files pipeline, guardrails, tracing & observability, and project-level resource management.

Platform teams that need a multi-tenant AI gateway, control plane, and operational surface for inference, vectors, files, and tracing.

Learn more

Console Platform

Cognipeer Console SDK

TypeScript SDK for Cognipeer Console

Official TypeScript/JavaScript SDK for Cognipeer Console. Provides type-safe access to chat completions, embeddings, vector operations, file management, agent tracing, and guardrails.

Application teams integrating with a Cognipeer Console deployment for chat, embeddings, vector, files, tracing, and guardrails.

Learn more

Studio Integration

Cognipeer Client SDK

Studio Integration SDK

Official JavaScript and TypeScript SDK for Cognipeer Studio. Connect applications to Studio conversations, channels, peers, users, and client-side tool execution from the browser or server.

Product and application teams integrating Cognipeer Studio into web apps, backends, and custom conversational experiences.

Learn more

Composable Runtime

Cognipeer Agent SDK

Deterministic TypeScript Agent Runtime

A deterministic TypeScript agent runtime for planning, safety, memory, and multi-agent orchestration. Zero-graph, message-first design with built-in summarization, guardrails, and structured tracing.

Teams building custom agent logic in TypeScript and needing deterministic execution, planning, and human-in-the-loop control.

Learn more

Composable Runtime

Cognipeer Agent Server

Agent Serving Infrastructure

A production-ready serving layer that registers, versions, and exposes multiple AI agents as secure, streaming-enabled REST services with Swagger/OpenAPI documentation.

Backend teams that need to publish agents as versioned APIs with streaming, auth, storage, and OpenAPI discovery.

Learn more

Composable Runtime

Cognipeer Chat UI

AI Conversational Interface Kit

A React component library for building modern, real-time conversational interfaces powered by AI agents. ChatGPT-style experience with streaming, tool transparency, and full customisation.

Frontend teams that need a production-ready conversational UI for agent and chat experiences with streaming and tool visibility.

Learn more