Features
Code completion with inline predictions
Answer engine for coding queries within IDE
Inline chat for real-time AI collaboration
Pochi agent: autonomous planning and execution of coding tasks
Data connectors (context providers) for enriched suggestions
Self-hosted deployment on consumer-grade GPUs
No external DBMS or cloud services required
Supports custom models via integrations
IDE support: VS Code, Neovim, IntelliJ, JetBrains IDEs
Doc Ingestion API for uploading personal documentation
Usage reports and analytics (Team tier)
Single Sign-On (SSO) support (Team/Enterprise)
Supports Vulkan, AMD ROCm, Hugging Face Spaces
Tabby Cloud usage-based billing with free tier
Flexible deployment (cloud or self-hosted)
@ai_fn decorator for LLM-powered Python functions
@ai_classifier decorator for text classification
Structured data extraction via Pydantic models
Agent loops with tool calling and function calling
Built-in streaming (SSE) support
Async-first API for concurrent applications
Rate limiting and automatic retries
LLM response caching for performance
Concurrency control for workload management
CLI tool for monitoring and debugging
SQLite state store for persistence
OpenAI and Anthropic model support
Embeddings generation for semantic search
Local execution with no cloud dependency
Self-hosted deployable as a library
