FlexiGPT

FlexiGPT is a local-first desktop workspace for multi-provider LLM chats.

It brings together reusable assistant presets, model presets, prompt templates, attachments, tools, and skills in one app while keeping conversations and configuration local.

Install

1. Download the latest release from GitHub Releases.
2. Install the package for your platform:
   • macOS: .pkg
   • Windows: .exe
   • Linux: .flatpak
   • Detailed installation steps are here
3. Launch FlexiGPT.

Quick start

• Get an API key for your provider.
  • OpenAI, Anthropic Claude, Google Gemini, xAI, MistralAI
  • OpenRouter, Hugging Face
• Add the key in Settings -> Auth Keys.
• Chat.

FlexiGPT does not bill you directly. Usage costs and limits come from the provider account behind the key you configure.

Key features

Multi-provider connectivity with built-in presets

• First-class builtin support for OpenAI, Anthropic, Google Gemini API, xAI, Mistral, Hugging Face, OpenRouter, and local llama.cpp
• Support for compatible custom endpoints across OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages style APIs
• Built-in providers and curated model presets for leading models so you can get started quickly without manually defining endpoints or defaults first
• API keys are stored securely through the OS keyring, not in plain-text exported settings

Unified chat workspace

• One interface for chats, tabs, attachments, prompts, tools, skills, presets, search, and exports
• Switch providers or models as you iterate
• Multi-tab conversations with local history search and resume flows
• Export the current conversation as JSON

Human-in-loop and agentic workflows

• Assistant presets bundle model choice, instructions, tools, and skills into reusable starting setups
• Tools can be attached per conversation and configured for manual review or auto-execution
• When an auto-execute tool is called, FlexiGPT can run it and automatically submit the result back to the model, enabling agentic workflows inside a normal chat flow
• Keep tools manual when you want tighter control over execution

Rich response rendering and inspection

• Markdown rendering with syntax-highlighted code blocks
• Mermaid diagram rendering with zoom and source or image export workflows
• KaTeX math rendering
• Citations, token usage, and per-message request/response details for inspection and debugging
• Message-level controls for copying, inspection, and follow-up iteration

Local-first context and history

• Local conversation storage and full-text search
• File, folder, image, PDF, and URL attachments
• Bundled offline docs shipped inside the app
• Use your own provider accounts; FlexiGPT does not proxy or bill model usage

Documentation

The main docs are bundled inside the app and mirrored in this repository under frontend/app/docs/content/.

User guide

• Installation
• Getting Started
• Core Concepts
• Chats, Composer, and Everyday Workflow
• Attachments, Tools, Skills, and Prompts
• Presets, Providers, and Settings
• Privacy, Storage, and Troubleshooting

Architecture

• Architecture Overview
• Backend Roles and Responsibilities
• Frontend Roles and Responsibilities
• Chats Workspace and Composer HLD

Built with

• Data storage: JSON and SQLite files in local filesystem.
• Go backend.
• Wails as a desktop application building platform.
• Official Go SDKs by OpenAI, Anthropic, and Google GenAI.
• Vite + React Router v7 frontend in Typescript. DaisyUI with TailwindCSS for styling.
• Tooling: Golangci-lint, Knip, ESLint, Prettier, GitHub actions

Contributing

Developer setup is documented in: devsetup.md

License

Copyright (c) 2024 - Present - Pankaj Pipada

All source code in this repository, unless otherwise noted, is licensed under the Mozilla Public License, v. 2.0. See LICENSE for details.