Get This Tool
HeyChat
Pricing
- Model
- Free
Summary
Most AI chat wrappers store your API keys in a plain-text config file, one accidental git push away from a billing surprise — HeyChat routes credentials through your OS keychain instead.
HeyChat is an open-source desktop chat client built on Tauri v2, React, and TypeScript. It handles real-time streaming conversations across Google Gemini, OpenAI, Groq, Anthropic, Ollama, and any OpenAI-compatible endpoint, with chat history stored locally in SQLite. The keychain-backed credential storage means your API keys never sit in a dotfile. Where it breaks: this is a chat interface, not a workflow builder — there are no tool calls, no agents running tasks on their own, no branching logic. Teams that need anything beyond a multi-provider chat window will hit that ceiling fast.
Bottom line: Pick HeyChat if you want a secure, local-first desktop client for switching between cloud and local models; plan a different tool the moment you need anything that runs a task without you typing the next message.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- API keys stored in the OS native keychain rather than plain-text files, so a leaked dotfile or accidental repo push does not expose your credentials.
- Provider-agnostic design covering Google Gemini, OpenAI, Groq, Anthropic, Ollama, and any OpenAI-compatible endpoint, so switching from a cloud model to a local one when costs or privacy requirements shift is a sidebar toggle rather than a reinstall.
- Local SQLite persistence for chat history, which means your conversation records stay on your machine and are not logged on a vendor's server.
- Real-time response streaming across all supported providers, so you read output as it generates rather than waiting for a full completion round-trip.
Cons
Sign in to edit- No tool-use, function calling, or agent loops of any kind — the moment a team needs a model to fetch data, run code, or chain steps without a human typing each prompt, HeyChat offers nothing and teams move to a tool like Open WebUI or a workflow builder that exposes those primitives.
- No API surface and no programmatic trigger, so the app cannot be embedded in a pipeline, called from a script, or integrated with external automation; teams that need HeyChat's output to feed into another system have no supported path and typically abandon it for a client that exposes an API or plugin interface.
- A small contributor base and 16-commit history at curation means production bugs may sit unresolved for extended periods, and teams running this in a shared or organizational context carry the maintenance burden themselves under the MIT license.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Linux, macOS, Windows
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-17T08:02:15.620Z
Best For
Who it's for
- Users wanting a desktop AI chat app
- Local data control with SQLite
- Switching between cloud and local models
What it does well
- Multi-provider AI conversations with streaming
- Local persistent chat history management
- Secure API key storage via OS keychain
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare HeyChat
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is HeyChat free?
- Yes — HeyChat is fully free to use. There is no paid tier.
- Is HeyChat open source?
- Yes. HeyChat is open source.
- Can I self-host HeyChat?
- Yes. HeyChat supports self-hosting on your own infrastructure.
- What platforms does HeyChat support?
- HeyChat is available on: Linux, macOS, Windows.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Every managed AI chat product eventually asks you to trust a third party with your conversation history, your API keys, or both. HeyChat is a desktop application that keeps both local: credentials go into your system’s native keychain (macOS Keychain, Windows Credential Manager, or the Linux equivalent), and conversation history lands in a SQLite database on your own machine. The core workflow is straightforward — open the app, pick a provider from the sidebar, type, and read the streamed response. Switching providers mid-session is a toggle, not a reconfiguration.
The differentiating feature is the keychain integration. The vendor’s README is explicit that API keys are stored in the system’s native keychain rather than plain-text config files. For anyone who has ever rotated keys after a .env file leaked into version control, that single design decision changes the security posture of the whole setup.
HeyChat fits one scenario well: a developer or power user who wants a single desktop interface to drive multiple AI providers — including a local Ollama instance — without handing conversation data to a SaaS intermediary. It does not fit teams that need structured outputs piped into downstream systems, agents that run tasks on their own, or any workflow that branches based on what a model returns. The tool has no API surface, so there is no way to trigger it programmatically or embed it in a pipeline. Teams that outgrow the chat-only model typically move to a tool with workflow primitives and accept the tradeoff of more complexity.
Built with Tauri v2 for the native shell, React and TypeScript for the frontend, and Vite for bundling. The project is MIT-licensed, self-hostable in the sense that you build and run the binary on your own machine, and carries a 16-commit history at time of curation — a young codebase with a small contributor base.