OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

AI Chatkit

AI Chatkit is an open-source, self-hostable web application template for building AI agent chat experiences with LangGraph, a FastAPI backend, a Next.js frontend and Chroma-based knowledge retrieval.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Chatkit — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Choose AI Chatkit when you need a modifiable application foundation that includes both an agent backend and a chat frontend, particularly for tool invocation, knowledge retrieval or multi-agent collaboration.

Who it is for

  • Developers building a custom web chat interface for AI agents.
  • Teams creating assistants that retrieve answers from a knowledge base.
  • Builders experimenting with specialized agents coordinated to handle different kinds of questions.

Documented uses

  • Create and orchestrate agents with custom behavior logic.
  • Connect agents to custom tools.
  • Build knowledge-base question answering with Chroma retrieval and bge-m3 embeddings.
  • Provide streamed chat responses through a web frontend.
  • Explore supervisor-managed collaboration among math, code and general-purpose agents.
Before you choose

Requirements & limits

The repository is public and identified as open source. Its README documents a local development setup with Python and Node-based frontend tooling.

  • The project includes backend and frontend services rather than only an agent framework.
  • LangGraph provides the documented agent orchestration structure, with custom orchestration logic placed in the backend agent directory.
  • Chroma supports knowledge-base storage and querying; the documented default embedding setup uses bge-m3 deployed locally through Ollama.
  • The README shows configuration examples for OpenAI, DashScope and DeepSeek, with credentials and provider access needed separately.
  • Chat streaming is supported through server-sent events, while chat history is saved in the local browser cache.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the backend and frontend locally

Follow the repository's documented commands to configure and start the backend and frontend services.

Before you start

  • Python backend dependencies managed with uv.
  • Node-based frontend tooling with pnpm.
  • A backend .env file configured with a database and model-provider settings; provider credentials are required for the selected provider.

Steps

  1. Rename the backend .env.example file to .env and configure the environment values, including a database URL and selected model-provider settings.

  2. In the backend directory, install uv if needed, run the command below, activate the created virtual environment, and run the command below.

    Documented command
    uv sync --frozen
    Documented command
    python app/run_server.py

  3. In the frontend directory, run pnpm install and then pnpm dev.

  4. The README gives http://localhost:3000/ as the frontend address after startup.

Expected outcome

The documented local setup starts the FastAPI backend and Next.js development frontend.

Guide limitations

  • These are repository instructions, not a compatibility guarantee or an execution test.
  • Using a model provider requires separately obtained credentials and provider access.
  • Knowledge-base retrieval also requires local Ollama deployment of bge-m3.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AI ChatkitCreate and orchestrate agents with custom behavior logic.Linux, Self-hosted, Server, WebThe repository is public and identified as open source. Its README documents a local development setup with Python and Node-based frontend tooling.
Insurance Agentic AIRoute insurance questions to a life, home or auto specialist.Docker, Self-hosted, Web
Anyloom Anythingllm Local AI Agentic Dytopo SwarmChat with a locally hosted language model through AnythingLLM.Docker, Self-hostedThe repository is public and licensed under MIT. The documented primary workflow is self-hosted with Docker; the README describes local hardware requirements and provides a browser-based AnythingLLM setup.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
pasonk/ai-chatkit · Official homepage title · retained in its source language
How we review sourcesSuggest a correction