better-chatbot
Formerly Better Chatbot. Navigator is an open-source AI workspace for agents, MCP and workflow automation.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/keinsaasforever--better-chatbot)HTML
<a href="/listings/keinsaasforever--better-chatbot"><img src="/api/listings/keinsaasforever--better-chatbot/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
> **Get your app running in minutes! No installation or payment required.**
You only need **one AI Provider API Key** (OpenAI, Claude, Gemini, etc.). Everything else runs on free tiers - database, file storage, and hosting.
π **[Click this guide to deploy your site with just a few clicks](docs/tips-guides/vercel.md)**
---
**Keinsaas Navigator** - A better open-source AI chatbot for individuals and teams, inspired by ChatGPT, Claude, Grok, and Gemini.
β’ **Multi-AI Support** - Integrates all major LLMs: OpenAI, Anthropic, Google, xAI, Ollama, and more β’ **Powerful Tools** - MCP protocol, web search, JS/Python code execution, data visualization β’ **Image Generation** - Create and edit images with AI models (OpenAI, Google Gemini, xAI) β’ **Automation** - Custom agents, visual workflows, artifact generation β’ **Collaboration** - Share agents, workflows, and MCP configurations with your team β’ **Voice Assistant** - Realtime voice chat with full MCP tool integration β’ **Intuitive UX** - Instantly invoke any feature with `@mention` β’ **Quick Start** - Deploy free with Vercel Deploy button
Built with Vercel AI SDK and Next.js, combining the best features of leading AI services into one platform.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md Β· README Β· 363 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # keinsaas Navigator β Community Edition
- <div align="center">
- <img src="docs/assets/navigator-banner.webp" alt="keinsaas Navigator: your operating system for the AI era. Powered by agents, skills, MCP and workflows." width="100%" />
- <sub>formerly <b>better-chatbot</b></sub>
- **An open-source AI chat and agent platform you can host yourself.**
- Talk to any model, attach your files, connect MCP tool servers, build workflows,
- and give agents a place to work β on infrastructure you control.
- [](LICENSE)
- [](https://discord.gg/9dwdAYKBPp)
- </div>
- ---
- ## Deploy to Vercel
- [](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fkeinsaasforever%2Fbetter-chatbot&project-name=better-chatbot&repository-name=better-chatbot&root-directory=apps%2Fweb&env=BETTER_AUTH_SECRET%2CAI_GATEWAY_API_KEY%2CCOMPOSIO_API_KEY%2CTENSORX_API_KEY%2CASSEMBLYAI_API_KEY%2CEXA_API_KEY%2CE2B_API_KEY%2CINNGEST_EVENT_KEY%2CINNGEST_SIGNING_KEY&envDefaults=%7B%22AI_GATEWAY_API_KEY%22%3A%22required%22%2C%22COMPOSIO_API_KEY%22%3A%22optional%22%2C%22TENSORX_API_KEY%22%3A%22optional%22%2C%22ASSEMBLYAI_API_KEY%22%3A%22optional%22%2C%22EXA_API_KEY%22%3A%22optional%22%2C%22E2B_API_KEY%22%3A%22optional%22%2C%22INNGEST_EVENT_KEY%22%3A%22optional%22%2C%22INNGEST_SIGNING_KEY%22%3A%22optional%22%7D&envDescription=Required%3A%20BETTER_AUTH_SECRET%20%28any%20long%20random%20string%2C%20e.g.%20openssl%20rand%20-base64%2032%29%20and%20AI_GATEWAY_API_KEY%20%28vercel.com%2Fai-gateway%3B%20serves%20every%20model%2C%20including%20realtime%20voice%29.%20Optional%2C%20leave%20at%20optional%20to%20switch%20the%20feature%20off%3A%20COMPOSIO_API_KEY%20%28connected%20apps%29%2C%20TENSORX_API_KEY%20%28EU-hosted%20models%29%2C%20ASSEMBLYAI_API_KEY%20%28voice%20transcription%29%2C%20EXA_API_KEY%20%28web%20search%29%2C%20E2B_API_KEY%20%28code%20sandboxes%29%2C%20INNGEST_EVENT_KEY%20and%20INNGEST_SIGNING_KEY%20%28scheduled%20agents%29.%20Add%20any%20of%20them%20later%20under%20Settings%2C%20Environment%20Variables.&envLink=https%3A%2F%2Fgithub.com%2Fkeinsaasforever%2Fbetter-chatbot%2Fblob%2Fmain%2Fdocs%2Fself-hosting.md%23vercel&stores=%5B%7B%22type%22%3A%22integration%22%2C%22integrationSlug%22%3A%22supabase%22%2C%22productSlug%22%3A%22supabase%22%2C%22protocol%22%3A%22storage%22%7D%5D)
- Two required values, a few optional ones. The button clones the repository,
- creates a free Supabase project for the database and file uploads, and asks
- for:
- | Variable | |
- | --- | --- |
- | `BETTER_AUTH_SECRET` | **Required.** Any long random string (`openssl rand -base64 32`). |
- | `AI_GATEWAY_API_KEY` | **Required.** From [vercel.com/ai-gateway](https://vercel.com/ai-gateway). Serves every model in the catalog, including realtime voice. |
- | `COMPOSIO_API_KEY` | Optional. Lets users connect Gmail, Slack, GitHub and more. [Free key](https://platform.composio.dev) |
- | `TENSORX_API_KEY` | Optional. EU-hosted models from our [partner](#partners) TensorX. |
- | `ASSEMBLYAI_API_KEY` | Optional. Voice transcription via [AssemblyAI](https://www.assemblyai.com/). |
- | `EXA_API_KEY` | Optional. Web search via [Exa](https://exa.ai/). |
- | `E2B_API_KEY` | Optional. Sandboxes that run generated code, via [E2B](https://e2b.dev/). Without it, code runs in the browser. |
- | `INNGEST_EVENT_KEY`, `INNGEST_SIGNING_KEY` | Optional. Scheduled agents and background jobs, via [Inngest](https://www.inngest.com/). Easiest: add the Inngest integration in Vercel, which sets both and connects the app. |
- The optional fields are pre-filled with `optional`; leave them like that and the
- feature stays off. You can add any key later under Settings β Environment
- Variables and redeploy. The database schema and the storage buckets are
- created during the build. Open the deployment and create an account; the first
- one becomes the administrator.
- Free Supabase projects pause after a week without use. If your app stops
- loading after a quiet week, open the project in the Supabase dashboard and
- click **Restore**.
- **Updates come to you.** After your first sign-in, the app asks once to
- **Turn on** automatic updates: it opens GitHub with the update check ready,
- and you click **Commit changes**. From then on your copy checks every week.
- When there is a new version, GitHub emails you a short guide: try the preview
- Vercel builds, then click **Merge**. Nothing changes in your live app until
- you do.
- Details and optional features: [docs/self-hosting.md](docs/self-hosting.md#vercel).
- ---
- ## Quick start (Docker)
- Three variables. That is the whole configuration to get chatting:
- ```bash
- git clone https://github.com/keinsaasforever/better-chatbot.git
- cd better-chatbot
- cp .env.example .env
- ```
- ```bash
- POSTGRES_URL=postgres://postgres:postgres@postgres:5432/better_chatbot
- BETTER_AUTH_SECRET= # npx @better-auth/cli@latest secret
- AI_GATEWAY_API_KEY= # https://vercel.com/ai-gateway
- ```
- ```bash
- docker compose -f docker/compose.yml up -d --build
- ```
- Open http://localhost:3000 and create an account. The first account becomes the
- administrator.
- **Why one model key?** Models are served through the Vercel AI Gateway, which
- fronts Anthropic, OpenAI, Google, Mistral, xAI, DeepSeek, Moonshot and more. You
- manage one key and one bill instead of seven, and you can switch models
- mid-conversation without touching configuration. If you would rather not use a
- gateway at all, point the app at Ollama, LM Studio, or any OpenAI-compatible
- endpoint β see [Models](#models).
- Prefer running it directly? See [docs/self-hosting.md](docs/self-hosting.md).
- ---
- ## See it in action
- ### Web search
- Ask about anything current and get an answer with its sources. Needs the optional `EXA_API_KEY`.
- <img src="docs/assets/demo-web-search.webp" alt="A chat that searches the web and answers with sources" width="100%" />
- ### Charts and tables
- One sentence in, a chart or an interactive table out.
- <img src="docs/assets/demo-chart.webp" alt="A chat that answers with a bar chart" width="100%" />
- ### Code execution
- Python and JavaScript run in a sandbox; results come back as tables and charts. Needs the optional `E2B_API_KEY`.
- <img src="docs/assets/demo-code.webp" alt="A chat that runs Python and shows the result as a table" width="100%" />
- ### Agents
- Mention an agent with `@` and it takes over the conversation with its own instructions and tools.
- <img src="docs/assets/demo-agent.webp" alt="Mentioning an agent with @ and getting a researched answer" width="100%" />
- ### Legal document review
- An example from the agent library: paste a clause or attach a contract, and the Legal Document Reviewer flags the risks and suggests changes.
- <img src="docs/assets/demo-legal.webp" alt="The Legal Document Reviewer agent analysing the risks of an NDA clause" width="100%" />
- ### Image generation
- Generate images right inside the conversation.
- <img src="docs/assets/demo-image.webp" alt="A chat that generates a watercolor image" width="100%" />
- ### Tools and MCP servers
- Connect your apps and any MCP server. The catalog of 250+ apps comes with the optional Composio integration.
- <img src="docs/assets/demo-mcp.webp" alt="Connected apps and the catalog of tools to connect" width="100%" />
- ### TensorX: EU-hosted, zero data retention
- Pick a model under **TensorX (0 Data Retention)** and your prompts go straight to EU infrastructure that keeps nothing. Needs the optional `TENSORX_API_KEY`; see [Partners](#partners).
- <img src="docs/assets/demo-tensorx.webp" alt="Choosing a TensorX model marked 0 Data Retention and chatting with it" width="100%" />
- ### Local models
- At the end of the model menu, **Add local Model** connects Ollama, LM Studio or any OpenAI-compatible server. Your data stays on your hardware.
- <img src="docs/assets/demo-local-models.webp" alt="Opening Add local Model at the end of the model menu and entering a server address" width="100%" />
- ### Voice input
- Click the microphone, speak, and your words are transcribed into the message box by AssemblyAI. Needs the optional `ASSEMBLYAI_API_KEY`.
- <img src="docs/assets/demo-voice.webp" alt="Clicking the microphone button, which turns red while recording" width="100%" />
- ### Desktop app (beta)
- The keinsaas Navigator desktop app for Windows and macOS, with local (stdio) MCP servers and native notifications. It connects to the cloud or to your own instance; see [What you get](#what-you-get).
- <img src="docs/assets/desktop-app.webp" alt="The keinsaas Navigator desktop app on Windows, showing the sign-in screen" width="100%" />
- ---
- ## What you get
- **Chat that does things.** Streaming conversations with tool calling, file
- attachments, image generation, and a sandboxed code runner. Mention an agent,
- workflow, or tool with `@` to pull it into the conversation.
- **Agents.** Give an agent a role, instructions, and a set of tools. Share it
- with your workspace or keep it private.
- **Skills.** Reusable capabilities an agent loads on demand, so a large toolbox
- does not have to sit in every prompt.
- **Projects with retrieval.** Group chats, documents, and tools around a piece of
- work. Uploaded documents are chunked, embedded, and searched with pgvector β
- no external service required. Point a project at a knowledge base if you want
- hosted retrieval instead.
- **Workflows.** Build a graph of steps β LLM calls, conditions, HTTP requests,
- code, templates β in a visual editor, publish it as a tool, and call it from any
- chat.
- **MCP tool servers.** Connect any Model Context Protocol server over HTTP or
- stdio, with OAuth support, per-tool customization and a cached tool list.
- Self-hosted instances can run stdio servers; the desktop app runs them locally.
- **Scheduled tasks.** Have an agent run on a schedule and report back.
- **Voice.** Realtime voice conversations through the gateway, plus transcription.
- **Voice device.** Pair an [M5Stack Atom Echo S3R](https://docs.m5stack.com/en/atom/Atom%20EchoS3R),
- press its button and talk: what you say is transcribed and handed to your
- agent with its tools, or turned into a new agent or a scheduled task. Pairing and device management are in
- the app; the device streams its audio through a small WebSocket bridge, which
- is not published for self-hosting yet
- ([#429](https://github.com/keinsaasforever/better-chatbot/issues/429)).
- **Desktop app (beta for self-hosting).** The keinsaas Navigator desktop app
- ([download at keinsaas.com](https://keinsaas.com)) adds local (stdio) MCP servers, which a server on Vercel cannot run, plus
- native notifications. On first launch it asks where to connect: pick **My own
- server** and enter your instance's address, e.g. `https://my-chatbot.vercel.app`.
- Connecting it to a self-hosted instance is in beta; tell us in
- [Discord](https://discord.gg/9dwdAYKBPp) what works and what does not. You can
- switch servers any time under **Change Serverβ¦** in the app menu.
- **Model routing.** Pick a model per message, or let the router choose from the
- catalog based on the task.
- ---
- ## Upgrading from 1.x
- This is a new major version. The layout is now a monorepo, the environment is
- different, and the schema has moved on considerably.
- **Back up your database first.** Then:
- ```bash
- pnpm install
- pnpm tsx scripts/upgrade/from-better-chatbot-1.ts --dry-run
- pnpm tsx scripts/upgrade/from-better-chatbot-1.ts --yes
- ```
- The upgrade preserves your users, chats, agents, MCP servers and workflows.
- Archives become projects, and the threads inside them stay linked. It is a
- one-way migration β this is why the backup matters.
- If you were setting per-provider API keys (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`
- and friends), replace them with a single `AI_GATEWAY_API_KEY`, or configure a
- local provider.
- ---
- ## Setup
- ### Vercel
- The [Deploy button](#deploy-to-vercel) above. Setting up an existing clone by
- hand is described in [docs/self-hosting.md](docs/self-hosting.md#vercel).
- ### Docker Compose
- The [quick start](#quick-start-docker) above. The bundled stack includes Postgres with
- pgvector. Add `--profile redis` if you want resumable chat streams.
- ### Local development
- ```bash
- pnpm install # writes .env from .env.example
- pnpm docker:pg # Postgres with pgvector on :5432
- pnpm db:migrate # apply the schema
- pnpm dev # http://localhost:3000
- ```
- Postgres **must** have the `pgvector` extension β document embeddings are stored
- as `vector(1536)`. The bundled image has it; managed Postgres usually offers it
- as a toggle.
- Useful commands:
- | Command | What it does |
- | --- | --- |
- | `pnpm check` | Lint, typecheck and unit tests β run before committing |
- | `pnpm test:e2e` | Playwright end-to-end tests |
- | `pnpm db:migrate` | Apply pending migrations |
- | `pnpm db:studio` | Browse the database |
- | `pnpm docker:redis` | Redis for resumable streams |
- ---
- ## Optional integrations
- Everything below is off until you configure it, except file uploads on Vercel,
- which the Supabase integration sets up for you. The server prints which
- features are disabled at startup, so you always know why something is missing.
- | Feature | Set | Without it |
- | --- | --- | --- |
- | File uploads | Nothing on Vercel: the Supabase integration sets it. Docker and local: `SUPABASE_URL`, `NEXT_PUBLIC_SUPABASE_URL`, `SUPABASE_SERVICE_ROLE_KEY` ([details](docs/self-hosting.md#storage)) | Attachments, avatars and generated images are disabled |
- | Knowledge bases | `AGENTSET_API_KEY` | Knowledge bases unavailable; project documents still search locally with pgvector |
- | Background jobs | `INNGEST_SIGNING_KEY`, `INNGEST_EVENT_KEY` | Scheduled tasks need your own cron (see below); the project brain runs right after each change instead of in the background |
- | Resumable streams | `REDIS_URL` | A stream ends when the viewer navigates away |
- | Code sandbox | `E2B_API_KEY` | Generated code runs in the in-browser worker only |
- | Web search | `EXA_API_KEY` | The web search tool is unavailable |
- | EU-hosted models | `TENSORX_API_KEY` | TensorX models (zero data retention) do not appear in the model picker |
- | Voice transcription | `ASSEMBLYAI_API_KEY` | Realtime voice still works; transcription does not |
- | Browser notifications | `NEXT_PUBLIC_VAPID_PUBLIC_KEY`, `VAPID_PRIVATE_KEY` | No notifications while the app is closed |
- | Connected apps | `COMPOSIO_API_KEY` | Users cannot connect Gmail, Slack, GitHub and other apps |
- | Observability | `SUPERLOG_PUBLIC_TOKEN` | Traces and logs stay local |
- **Running without Inngest.** Scheduled tasks and the sandbox reaper are plain
- HTTP endpoints. Set `SCHEDULED_TASK_SECRET` and call them from any cron:
- ```bash
- curl -X POST https://your-instance/api/scheduled-tasks/cron \
- -H "X-Scheduled-Task-Auth: $SCHEDULED_TASK_SECRET"
- ```
- ---
- ## Models
- The gateway is the default and covers the whole catalog. You can also:
- - **Run models locally.** Connect Ollama, LM Studio, or any OpenAI-compatible
- endpoint from the model picker. Nothing leaves your machine, and it needs no
- server configuration β each account sets up its own.
- - **Use [TensorX](#partners).** EU-hosted inference with zero data retention,
- reached directly rather than through the gateway. Set `TENSORX_API_KEY`.
- - **Add any OpenAI-compatible provider** with `OPENAI_COMPATIBLE_DATA`:
- `pnpm openai-compatiable:init && pnpm openai-compatiable:parse`.
- ---
- ## Partners
- **[TensorX](https://tensorx.ai/)** β EU-hosted model inference with zero data
- retention. The Community Edition talks to TensorX directly rather than through a
- gateway, so prompts go straight to TensorX's EU infrastructure. Create a key at
- [tensorx.ai](https://tensorx.ai/), set `TENSORX_API_KEY`, and its models appear
- in the model picker next to the gateway's. See its
- [trust and security](https://tensorx.ai/trust-security/) page and
- [DPA](https://tensorx.ai/dpa/).
- TensorX is optional. Without the key everything else works as before.
- ---
- ## Community
- - **[Discord](https://discord.gg/9dwdAYKBPp)** β questions, help, and what
- people are building
- - **[Issues](https://github.com/keinsaasforever/better-chatbot/issues)** β bugs
- and feature requests
- - **[CONTRIBUTING.md](CONTRIBUTING.md)** β how to work in this repository
- ---
- ## This edition, and the hosted one
- This repository is the Community Edition of
- [keinsaas Navigator](https://keinsaas.com), formerly known as better-chatbot. The
- repository keeps its name, so existing links, forks and automatic updates keep
- working. Everything above is here, in full,
- with no usage caps and no telemetry.
- What Navigator adds is what teams need and single users do not: shared team
- workspaces with member management and invitations, per-member AI budgets and
- org-wide model policy, billing, a managed workflow builder, and a Slack bot.
- If you are running this for yourself or a small group, you are not missing
- anything β that is the point.
- ---
- ## License
- MIT. See [LICENSE](LICENSE).
- Originally forked from [cgoinglove/better-chatbot](https://github.com/cgoinglove/better-chatbot),
- whose work this is built on.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If itβs helped, pass it on.