Features
Run multiple open-source models locally (Mistral, Llama, Phi, etc.)
Up to 5 concurrent model sessions (multi-weave)
Contextual thread fusion to chain model outputs
Universal model manager supporting Hugging Face, Ollama, GGUF, GPTQ
Automatic quantization optimization (4-bit, 8-bit, FP16)
Native file looming indexing up to 100K tokens
Real-time collaborative editing over local WebSocket
Intelligent prompt looms for multi-model code review
Cross-platform support: Windows (x64), macOS (Intel+Apple Silicon), Linux (x64/ARM)
Multilingual interface in 12 languages
24/7 offline availability with no server dependencies
Privacy-first offline mesh with no telemetry or cloud relays
No user accounts or subscription required
Supports fast weft (<200ms response) with 1-3B models
Supports warp thread with 7-70B models for complex tasks
GPU-accelerated terminal rendering
Multi-agent orchestration with model routing
Support for OpenAI, Claude Code, Codex, Warp Agent
Codebase indexing for agent context
Granular permission controls for agents
Oz cloud platform for agent orchestration
SDK/CLI for programmatic agent launches
Seamless local-to-cloud agent handoff
First-party Warp Agent with advanced harness
Open-source terminal code
Credit caps and usage visibility for teams
Private deployment and self-hosting
Warp Drive for sharing notebooks and workflows
