Deploy Now

Stars

7,122

Forks

1,594

Watchers

71

Developer links

big-AGI

big-AGI is an open-source generative AI workspace that provides a unified, local-first interface for orchestrating multi-model reasoning, automated code execution, and custom persona workflows across private infrastructure. Users query multiple large language models simultaneously through the Beam scatter-gather engine, which prompts independent AI systems in parallel, compares candidate completions side by side, and merges optimal passages into a single refined response. Knowledge workers assemble tailored AI personas equipped with specialized system instructions, custom temperature settings, and predefined document context to handle domain-specific tasks ranging from architectural design reviews to legal contract analysis. The application renders rich multimedia outputs including interactive Mermaid sequence diagrams, LaTeX mathematical formulas, syntax-highlighted code blocks with live execution previews, and AI-generated image generation canvases. Teams integrate local inference servers like Ollama and LocalAI alongside commercial API endpoints to route confidential datasets strictly through internal networks while monitoring per-prompt token usage and operational latency. Users attach complex PDF documents, spreadsheets, and source code repositories for automatic parsing and semantic retrieval, while local-first storage engines ensure private chat transcripts and custom presets remain encrypted on host drives. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

big-AGI
big-AGI
big-AGI
big-AGI
big-AGI
big-AGI

Benefits

  • Parallel Multi-Model Beam Reasoning Engine
  • Dispatches prompts across multiple LLM endpoints simultaneously using a scatter-gather architecture, allowing operators to compare candidate responses side by side and combine optimal answers into verified summaries.
  • Unified Multi-Vendor Model Routing Architecture
  • Connects to over twenty commercial AI providers and self-hosted inference servers like Ollama and LocalAI through standardized API layers, eliminating proprietary client dependencies and third-party vendor lock-in.
  • Air-Gapped Private Infrastructure Deployment
  • Operates completely within self-hosted Docker containers backed by client-side browser storage and encrypted volumes, guaranteeing that confidential prompts and sensitive documents never escape internal networks.
  • Customizable Domain-Specific Persona Automation
  • Enables teams to configure tailored agent personas with distinct system instructions, temperature limits, and contextual knowledge bases to automate specialized technical writing, coding, and code analysis.

Features

  • Beam Multi-Model Chat
  • Executes scatter-gather prompts across multiple LLM backends simultaneously, displaying concurrent completion streams for comparative evaluation and automated response synthesis.
  • AI Persona Studio
  • Configures customizable agent personas with dedicated system prompts, temperature dials, and response presets tailored for specialized programming, translation, and research workflows.
  • Interactive Code Execution
  • Renders syntax-highlighted code blocks with integrated copy utilities, markdown parsing, and client-side execution environments for real-time script evaluation and debugging.
  • Multi-Provider API Gateway
  • Integrates with OpenAI, Anthropic, Google Gemini, Groq, Mistral, and local Ollama instances via authenticated REST endpoints with token usage tracking.
  • Document And Image Analysis
  • Ingests PDF manuals, text files, and image attachments directly into conversations for multimodal inspection, vector search indexing, and automated summarization.
  • Diagram And Formula Rendering
  • Transforms markdown responses into dynamic Mermaid diagrams, KaTeX mathematical formulas, and structured data tables directly within the interactive conversation canvas.