Newest Releases

Aider

✓

Open-source AI pair programming in your terminal with automatic git commits

Aider (v0.85.4) is a powerful open-source AI pair programming tool that runs entirely in your terminal. It excels at making real-world changes to codebases, automatically creating git commits with descriptive messages. Aider works with all major AI models including GPT-5, Claude 4 Opus, Claude 4 Sonnet, Claude 3.7 Sonnet, DeepSeek R1, GPT-4o, and local models, making it budget-friendly and flexible. The framework works best with models like Claude 3.7 Sonnet, DeepSeek R1, and GPT-4o. Perfect for developers who prefer terminal-based workflows, Aider can edit multiple files simultaneously and understands your entire project structure.

Amazon Q Developer

✓

AWS-optimized AI code generator with security scanning and CLI completions

Amazon Q Developer (formerly CodeWhisperer) is AWS's AI-powered coding assistant optimized for Amazon Web Services development. Note: As of November 24, 2025, Q Developer CLI is being rebranded to 'Kiro CLI'. The service now features autonomous agents for multi-step tasks, advanced conversational AI for AWS resource management, and enhanced cost management capabilities. With project-wide context analysis, sophisticated code transformations (like Java 8 to Java 17 migration), AWS API optimization, security vulnerability scanning, and CLI completions, it's perfect for cloud developers working in the AWS ecosystem. Free for individuals with an AWS account.

Claude Haiku 4.5

✓

Fast and affordable coding model

Released October 15, 2025, Claude Haiku 4.5 is Anthropic's latest small model that delivers similar coding performance to Sonnet 4 at a third of the cost and more than twice the speed. This generation of Haiku is the first to include features previously exclusive to higher-tier models, including extended thinking capabilities, computer use, and enhanced context awareness.

Claude Sonnet 4.5

✓

The best coding model in the world

Released September 29, 2025, Claude Sonnet 4.5 is the best coding model in the world, achieving 77.2% on SWE-Bench Verified benchmark, outperforming competitors like GPT-5. It's the strongest model for building complex agents and the best model at using computers. Features extended thinking mode for complex problem-solving and is Anthropic's most aligned frontier model for safety. Shows substantial gains in reasoning and math.

AutoGen

✓

Microsoft's multi-agent conversation framework for complex AI workflows

AutoGen is Microsoft's open-source framework for building multi-agent AI systems. Version 0.4 (early 2025) introduced a major architectural redesign with an event-driven foundation, segmenting the framework into distinct components: AutoGen-Core, AgentChat, AutoGen-Extensions, and a rebuilt low-code AutoGen Studio. It enables specialized agents to collaborate on complex tasks through async conversations with human-in-the-loop capabilities. Features superior scalability, observability, and cross-language support for Python and .NET.

Bolt.new

✓

Build and deploy full-stack applications in minutes with AI from StackBlitz

Bolt.new by StackBlitz is an open-source, AI-powered development environment that creates complete full-stack applications from natural language prompts. Built on StackBlitz's WebContainers technology, it runs a full-stack environment including Node.js servers and package managers directly in the browser. Can now handle projects 1,000 times larger than before. Bolt Cloud provides enterprise-grade backend infrastructure. Bolt can build and deploy production-ready apps in 8-10 minutes with full control over generated code, real-time preview, and instant deployment.

Anthropic Claude API

✓

Access Claude Opus 4.5, Sonnet 4.5, and more with 200K+ context window

The Anthropic Claude API provides access to Claude's family of models, including Claude Opus 4.5 (launched November 24, 2025) and ultra-fast Sonnet 4.5. November 2025 updates introduced major API features: Programmatic Tool Calling and Tool Search to reduce token consumption, an 'effort' parameter to balance cost and performance, and guaranteed structured outputs in JSON format. With a massive 200K+ token context window and industry-leading reasoning capabilities, Claude excels at complex tasks like code analysis, document processing, and agentic workflows. Opus 4.5 leads SWE-bench Verified. Known for strong coding performance and safety, Claude is trusted by enterprises and developers worldwide.

Claude Code

✓

Official CLI from Anthropic for terminal-based AI coding with Claude Opus 4.5

Claude Code is Anthropic's official command-line interface that brings Claude's powerful AI capabilities directly to your terminal. Integrated into Anthropic's Pro, Max, and Team subscription plans, it utilizes both Sonnet 4.5 and Opus 4.5 models. Key workflow features include providing project-specific context via a CLAUDE.md file and triggering extended thinking mode for complex problem-solving. Claude Code excels at understanding entire codebases, performing complex multi-file refactoring, and executing tasks autonomously with human oversight. The Opus 4.5 model delivers 65% fewer tokens for long-horizon tasks and 30-minute autonomous coding sessions.

Claude Opus 4.5

✓

Anthropic's most powerful AI model with state-of-the-art coding and agentic capabilities

Claude Opus 4.5 is Anthropic's flagship AI model, released November 24, 2025. It delivers state-of-the-art performance on coding benchmarks, leading SWE-bench Verified and outperforming all frontier models. With the new effort parameter, developers can customize the balance between speed and capability. The model features context compaction for longer-running agentic sessions, using up to 65% fewer tokens for long-horizon coding tasks. Opus 4.5 is the most robustly aligned model to date, with industry-leading resistance to prompt injection attacks.

Codeium (Now Windsurf)

✓

Free AI code completion - Note: Rebranded to Windsurf in April 2025

**Note: Codeium has been rebranded to Windsurf (April 2025) and was subsequently acquired by Cognition AI (July 2025). See our Windsurf listing for the latest information.** Codeium was a free AI-powered code completion tool that offered unlimited completions for individual developers. Supporting 70+ programming languages and 40+ IDEs, it provided fast, accurate AI suggestions powered by in-house models. The product has evolved into Windsurf, which includes the Cascade agentic chat feature and support for frontier models like Claude Opus 4.5, Gemini 3 Pro, and GPT-5.1.

Windsurf

✓

Enterprise AI IDE with proprietary SWE-1.5 model for deep codebase understanding

Windsurf is an AI IDE originally created by Exafunction as the evolution of Codeium (rebranded April 2025) and acquired by Cognition AI (creators of Devin) in July 2025. Features the Cascade agentic chat for conversational coding and a context-awareness engine that indexes your codebase for personalized suggestions. It offers AI Codemaps for visual codebase navigation, Fast Context for rapid understanding of large projects. Now supports frontier models including Claude Opus 4.5, Gemini 3 Pro, and GPT-5.1 (added November 2025). Designed for professional teams working with complex, multi-file codebases.

Vercel AI SDK

✓

The AI Toolkit for TypeScript

The AI SDK is the TypeScript toolkit designed to help developers build AI-powered applications with Next.js, Vue, Svelte, Node.js, and more. Integrating LLMs into applications is complicated and heavily dependent on the specific model provider you use. The AI SDK abstracts away the differences between model providers, eliminates boilerplate code for building chatbots, and allows you to go beyond text output to generate rich, interactive components.

Replit

✓

Cloud-based IDE with Ghostwriter AI and instant deployment for rapid development

Replit is a collaborative, browser-based IDE with powerful AI capabilities through Ghostwriter and Agent 3. Build, run, and deploy applications entirely in the browser with support for 50+ languages. Perfect for education, rapid prototyping, and collaborative coding, Replit offers instant deployment, real-time collaboration, and AI-powered code generation. No setup required - start coding immediately.

GPT-5

✓

Next-generation multimodal AI model

A multimodal large language model developed by OpenAI, it is a system that contains a fast, high-throughput model, a deeper reasoning model, and a real-time router that decides which model to use based on conversation type, complexity, tool needs, and explicit user intent.

OpenAI Codex

✓

The AI model that powers GitHub Copilot - Evolving into an Agent

OpenAI Codex was the original AI model capable of translating natural language to code, powering tools like GitHub Copilot. While the original standalone API was deprecated in 2023, the 'Codex' brand was revived in late 2025 as an autonomous software engineering agent. OpenAI continues to release specialized coding models under the Codex lineage, such as GPT-5.1-Codex, ensuring it remains at the forefront of AI code generation.

Devin AI

✓

AI Software Engineer

An agent-native IDE experience that can handle complex, multi-step engineering tasks, including writing and debugging code, planning, and collaborating with users.

Cursor

✓

The AI-first code editor built to make you extraordinarily productive

Cursor is an AI-powered code editor built on a fork of VS Code. It allows you to write, edit, and chat about your code with state-of-the-art AI models like GPT-4.1, Claude 3.5 Sonnet, and Gemini 2.5 Pro. Cursor integrates AI directly into the editor with features like Tab (autocomplete), Composer (multi-file editing), and Agent (autonomous tasks), enabling a flow state where you can build software faster than ever before.

Gemini 3 Pro

✓

State-of-the-art reasoning and multimodal model

State-of-the-art reasoning and multimodal understanding model with powerful agentic and coding capabilities.

LangChain & LangGraph

✓

Build production-grade AI agents

LangChain is the fastest way to build an AI agent. LangGraph is a lower level framework and runtime, useful for highly custom and controllable agents, designed to support production-grade, long running agents.

AutoGen

✓

Open-Source Framework for Agentic AI

An open-source framework for orchestrating AI agents, reimagined in v0.4 with an asynchronous, event-driven architecture for dynamic, scalable workflows.

GPT-4o

✓

Faster and more affordable GPT-4

A multi-modal model that's 2x faster, 50% cheaper and has 5x higher rate limits compared to the latest GPT-4 Turbo release.

Phind

✓

The Developer's Answer Engine

A specialized AI-powered answer engine for developers that performs real-time web searches across curated sources to synthesize a single, comprehensive answer with citations.

Warp Terminal

✓

The Agentic Development Environment

A cutting-edge, AI-powered terminal designed to enhance developer productivity. Built at the terminal level, meaning it can write code, respond to system events, and even deploy to prod.

Lovable

✓

Build complete apps through chat - 20x faster than traditional coding

Lovable (formerly GPT Engineer) is an AI-powered platform that builds complete applications through natural conversation. Claiming 20x faster development than traditional coding and reaching $200M ARR, Lovable enables anyone to create full-stack applications without extensive coding knowledge. Perfect for entrepreneurs and non-technical founders who need to build MVPs quickly.

DeepSeek Coder

✓

Open-source coding LLM with 236B parameters and ultra-affordable API pricing

DeepSeek Coder is a powerful open-source coding LLM with 236 billion parameters and a 128K context window. Released in June 2024 (V2), it supports 338+ programming languages with an MoE (Mixture of Experts) architecture. DeepSeek offers exceptional performance matching GPT-4 Turbo at extremely affordable prices ($0.14-0.28 per million tokens). Perfect for budget-conscious developers and teams who need powerful AI coding capabilities without breaking the bank.

Continue

✓

Open-source, model-agnostic AI coding assistant with full customization

Continue is the leading open-source AI coding assistant that works with any LLM. Fully customizable and privacy-first, Continue allows developers to use their preferred AI models (OpenAI, Anthropic, local models, etc.) with custom prompts and configurations. It seamlessly integrates with VS Code and JetBrains IDEs, offering autocomplete, chat, and refactoring capabilities. Perfect for developers who want control over their AI tools, Continue supports self-hosting and can work entirely offline with local models.

Cody

✓

Enterprise AI assistant with codebase-wide context and zero data retention

Cody by Sourcegraph is an enterprise-focused AI coding assistant that understands your entire codebase. With multi-repo context awareness, BYOK (Bring Your Own Key) support, and SOC 2 compliance, Cody is designed for large organizations with strict security requirements. It offers zero data retention and works across multiple repositories, making it ideal for enterprises managing complex, multi-project environments.

Sweep AI

✓

AI junior developer that handles GitHub issues and clean up technical debt

Sweep AI is an AI-powered junior developer that automatically handles GitHub issues, writes code, and cleans up technical debt. It reads your codebase, plans changes, and creates pull requests for you to review. Ideal for offloading routine maintenance, bug fixes, and small feature requests, Sweep AI helps teams move faster by automating the coding grunt work.

Tabnine

✓

Privacy-first AI code assistant with personalized models and zero data retention

Tabnine is an AI code completion tool that prioritizes privacy and security. With support for 30+ languages and personalized team learning, Tabnine offers zero data retention and on-premise deployment options. It provides context-aware code suggestions while ensuring your code never leaves your environment. Perfect for enterprises and privacy-conscious developers, Tabnine combines powerful AI capabilities with strict security standards.

LangChain

✓

Framework for building LLM applications with chains, agents, and RAG

LangChain is the leading open-source framework for building applications with large language models. It provides composable components for chains, agents, memory, and tool use, making it easy to build complex AI applications. With support for RAG (Retrieval Augmented Generation), multi-agent systems, and production-grade deployments via LangSmith, LangChain is the foundation for thousands of AI applications worldwide.

LangGraph

✓

Graph-based framework for building stateful, multi-step AI agents

LangGraph is a specialized framework from LangChain for building stateful, multi-step AI agents with complex workflows. Using graph-based architecture, LangGraph enables branching logic, conditional workflows, and persistent state management. Perfect for building sophisticated AI agents that need to handle complex decision trees and multi-step reasoning with full control over execution flow.

GitHub Copilot

✓

Industry-leading AI code completion with 100M+ accepted suggestions daily

GitHub Copilot is the industry's most widely adopted AI coding assistant, developed by GitHub and Microsoft. With over 100 million suggestions accepted daily, Copilot provides intelligent code completion, chat-based assistance, and multi-model support including GPT-4.1, Claude 3.5 Sonnet, and Gemini 2.5 Pro. It integrates seamlessly with VS Code, Visual Studio, JetBrains IDEs, and Neovim, offering developers context-aware suggestions that learn from billions of lines of code. Copilot now offers a generous free tier with 2,000 completions per month, making it accessible to all developers.

Gemini Code Assist

✓

Enterprise-grade AI code assistance from Google Cloud

Gemini Code Assist (formerly Duet AI) is Google Cloud's enterprise-grade AI coding assistant. Powered by the Gemini 1.5 Pro and Gemini 2.5 models, it offers robust code completion, generation, and chat capabilities within popular IDEs. With a massive 1 million token context window for local codebase awareness and enterprise indemnification, it's designed for large-scale, secure software development.

CrewAI

✓

Role-based multi-agent task execution framework for collaborative AI teams

CrewAI is an open-source framework for orchestrating role-based multi-agent AI systems. Designed with team-oriented agents and task delegation, CrewAI is beginner-friendly while being powerful enough for production use. Agents work together like a crew, each with specialized roles, making it perfect for building AI systems that mimic human team workflows.

Amazon CodeWhisperer (Merged)

✓

AWS AI coding companion - Now Amazon Q Developer

Amazon CodeWhisperer has been fully merged into Amazon Q Developer as of April 30, 2024. It is no longer a standalone product. All features, including real-time code suggestions, security scanning, and reference tracking, are now available within the Amazon Q Developer experience. Please refer to the Amazon Q Developer entry for current information.

Mintlify

✓

AI-powered documentation generator with contextual improvements and inline suggestions

Mintlify is an AI-powered documentation platform that automatically generates beautiful docs from your code. With contextual improvements, inline suggestions, and support for modern documentation sites, Mintlify makes it easy to create and maintain high-quality documentation. Perfect for open-source maintainers and teams who need professional docs without manual effort.

Mutable AI (Acquired)

✓

AI-accelerated software development - Integrated into Google Code Wiki

Mutable AI was an AI development tool known for its 'Auto Wiki' feature and codebase interaction capabilities. In December 2024, Mutable AI was acquired by Google. Its technology and team have been integrated into Google to build 'Code Wiki', a next-generation documentation and codebase understanding tool. As a standalone product, Mutable AI is no longer accepting new subscriptions.

Pieces for Developers

✓

Your on-device AI workflow assistant for code snippets and context

Pieces for Developers is an AI-enabled productivity tool designed to manage your development workflow. It captures code snippets, screenshots, and workflow context, making them searchable and reusable. With an on-device-first architecture, it ensures privacy while offering powerful AI capabilities like code explanation, transformation, and generation. It seamlessly integrates with your IDE, browser, and collaboration tools to reduce context switching.

StarCoder 2

✓

State-of-the-art open-access code LLM by BigCode

StarCoder 2 is a family of open-access Large Language Models for code, developed by BigCode (Hugging Face & ServiceNow). Released in February 2024, it comes in 3B, 7B, and 15B parameter sizes. Trained on The Stack v2 (4 trillion tokens), it offers state-of-the-art performance, transparency, and a 16K context window, making it a powerful tool for code completion and generation.

Stenography

✓

AI-powered automatic code documentation and explanation

Stenography is an AI tool designed to automate code documentation. It reads your code and generates plain English explanations, helping developers understand complex codebases quickly. With VS Code and Chrome extensions, it integrates seamlessly into your workflow, providing instant documentation and context for any code snippet.

Supermaven (Sunset)

✓

Ultra-fast AI code completion - Merged into Cursor

Supermaven was known for its 1 million token context window and lightning-fast speeds. As of November 2024, Supermaven has been acquired by Cursor and the product is being sunset. Existing users are provided free autocomplete inference for the time being, but the standalone product is no longer accepting new signups. Its technology is being integrated into the Cursor IDE.

Google Gemini API

✓

Access Gemini 2.5 Pro and 3 Pro models with competitive pricing and Firebase integration

Google's Gemini API provides access to powerful multimodal AI models including Gemini 2.5 Pro and 3 Pro. With OpenAI-compatible endpoints, Firebase integration, and highly competitive pricing, Gemini is an excellent choice for developers building AI applications. The API offers strong performance on coding tasks, multimodal understanding, and seamless integration with Google Cloud Platform.

OpenAI API

✓

Access to GPT-4, GPT-4.5, and cutting-edge AI models for developers

The OpenAI API provides access to state-of-the-art AI models including GPT-4, GPT-4.5, and DALL-E. With multimodal capabilities, structured outputs, and extensive documentation, OpenAI's API is the foundation for thousands of AI applications. Pay-per-use pricing makes it accessible for projects of all sizes, from small prototypes to enterprise applications processing billions of tokens.

Project IDX

✓

Google's AI-powered browser-based development environment with Gemini integration

Project IDX is Google's experimental AI-powered, browser-based development environment. With deep Gemini integration, cloud workspaces, and multi-platform development support, Project IDX enables full-stack development entirely in the browser. Currently in beta and free to use, it represents Google's vision for the future of cloud-based development.

Qodo

✓

AI-powered testing and code integrity platform for quality-focused development

Qodo (formerly CodiumAI) is an AI-powered platform focused on testing and code integrity. With Qodo Gen for IDE refactoring and Qodo Merge for PR review, it helps developers maintain high code quality through automated test generation, code analysis, and pull request reviews. Perfect for QA engineers and test-driven development teams.

v0

✓

AI-powered React component generator by Vercel with Tailwind and shadcn/ui

v0 by Vercel is a generative UI system that creates beautiful React components from text prompts. Built on Next.js with Tailwind CSS and shadcn/ui, v0 generates production-ready, accessible components that follow modern web development best practices. Perfect for designers and developers who want to rapidly prototype interfaces or kickstart projects with high-quality components. v0 understands design systems and creates consistent, customizable code you can export and use immediately.