#773 · Primary category: AI Agents & Automation

HyperChat

agent chat-application llm local-agent mcp modelcontextprotocol

HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.

Project last updated:08/26/26

GitHub Stars

708

Forks

73

Contributors

5

License

Apache-2.0

Why we included this project

HyperChat is a local-first agent runtime that treats AI configuration as code. You point it at OpenAI, Claude, Gemini, Kimi, Qwen, or any compatible endpoint, then layer MCP tools on top so the assistant can read and edit local files and run scripts as part of real project work. The standout is the `.hyperchat/` directory: agents, workspaces, and MCP services live there as plain files you can commit to Git and move between machines, which makes setups reproducible and reviewable instead of locked inside a cloud dashboard. A Web front end handles multi-workspace project work, while a CLI mode suits quick conversations and CI/CD automation, and both share the same agent definitions. Teams that want a self-hosted agent layer with real tool access and portable configuration will get solid mileage out of it.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category