Release Notes

New updates and improvements to the fastest code application system

Dec 21, 2025

WarpGrep - AI-Powered Codebase Search

Features

  • Natural language codebase search with AI agent integration
  • Native adapters for Anthropic, OpenAI, Gemini, and Vercel AI SDK
  • Remote sandbox execution support (E2B, Modal, Daytona, Docker, SSH)
  • Direct usage API for custom integrations
  • Provider-agnostic Zod schemas for custom integrations
  • Seamless integration with existing agent workflows

WarpGrep enables AI agents to utilize a sub-agent to search and navigate codebases using natural language queries, making it easier to build powerful coding assistants.

May 25, 2025

Ultra-Fast Streaming & Enhanced Context

Features

  • Increased streaming speed to 10,500+ tokens/second for large file applications
  • Enhanced context window support for files up to 1M tokens
  • Smart context reranking
  • New batch processing API for multiple file updates
  • Improved error recovery for partial applications

Bug Fixes

  • Fixed edge case in merge conflict resolution
  • Resolved streaming buffer issues for very large files
  • Improved handling of malformed update snippets

This release focuses on speed and reliability for enterprise-scale code applications.

May 20, 2024

Morph Apply 2.0 - Production Ready

Features

  • 🚀 Production-grade reliability with 99.9% uptime
  • ⚡ 10,500+ tokens/second streaming performance
  • 🔧 Support for all major programming languages and file formats
  • 🎯 Intelligent diff detection and conflict resolution
  • 📊 Real-time application metrics and monitoring
  • 🔐 Enterprise security with SOC 2 compliance
  • 🌐 Global edge deployment for minimal latency

Major milestone release bringing Morph Apply to production readiness.

May 3, 2024

Developer Experience Overhaul

Features

  • New interactive playground with live preview
  • One-click integration with Continue.dev
  • Enhanced API documentation with interactive examples
  • Real-time collaboration features for team workflows
  • Custom model support for GPT-4, Claude, Gemini, and more

Bug Fixes

  • Fixed authentication flow for team accounts
  • Resolved API rate limiting edge cases
  • Improved error messages for debugging

April 30, 2024

Multi-Model Support & Performance

Features

  • Native support for Claude 3.5 Sonnet, GPT-4o, and Gemini Pro
  • Model-specific optimization for different code types
  • Automatic model selection based on file type and size
  • Parallel processing for multiple file updates
  • Advanced caching system reducing API costs by 60%

Bug Fixes

  • Fixed timeout issues for very large codebases
  • Improved memory management for concurrent requests
  • Resolved edge cases in TypeScript interface merging

April 25, 2024

Enterprise Features & Scale

Features

  • Team collaboration with shared workspaces
  • Advanced usage analytics and billing controls
  • Custom deployment options for enterprise customers
  • Webhook support for CI/CD integration
  • Priority support with dedicated engineering resources

April 5, 2024

Intelligent Context & Accuracy

Features

  • Smart context selection reducing hallucinations by 40%
  • File-type specific merge strategies
  • Syntax-aware conflict resolution
  • Automatic backup and rollback capabilities
  • Enhanced support for configuration files and documentation

Bug Fixes

  • Fixed issues with nested function edits
  • Improved handling of indentation and formatting
  • Resolved conflicts in import statement merging

This release significantly improves edit accuracy and reduces the need for manual cleanup.

April 1, 2024

Morph Apply Launch 🚀

Features

  • 🎯 Core apply functionality with 1000+ tokens/second
  • 📝 Support for code, documentation, and configuration files
  • 🔄 Real-time streaming of applied changes
  • 🛡️ Safe merge algorithms preventing data loss
  • 🔗 OpenAI-compatible API for easy integration
  • 📚 Comprehensive documentation and examples
  • 💻 Developer-friendly playground interface

Initial public release of Morph Apply - the fastest way to apply LLM-generated code updates.