Developer
AI tools.

Agenta is the open-source workspace for your agents. Build agents through chat, improve them with feedback, and share them with your whole team — self-hosted or in the cloud.

Replace your help desk with one AI employee that handles every customer on every channel. Vertical presets for home services, dental, legal, and auto. Self-serve, flat pricing.

AI-powered SQL query builder enables you to quickly build SQL queries without any knowledge of SQL for beginners.

An AI pair-programming tool that works with local code repositories through a terminal-based workflow.

Accelerate software development with Amazon Q Developer — an AI coding assistant that writes, debugs, and refactors code natively in your IDE.

An AI coding assistant from AWS for code generation, application modernization, and developer support.

Amazon Q Developer for command line enhances your terminal experience with AI-powered features including command autocompletion, natural language chat, and code generation for hundreds of popular CLIs.

Build faster with AskCodi: multi-model AI chat, code generation, refactoring, and custom agents. OpenAI-compatible API, IDE integrations, and developer-first workflows.

An AI coding platform for navigating large codebases and supporting professional software development.

A framework for prototyping, programming, and deploying conversational single- and multi-agent AI systems: use the web-based Studio to build no-code prototypes, then develop Python AgentChat/Core workflows and extensions to create scalable, event-driven multi-agent applications.

Secure, private, fast. We run the open-weight model that you choose as a dedicated deployment, or we route 300+ models through one endpoint. Verified speed.

BLOOM is BigScience’s autoregressive language-model family, trained across 46 natural languages and 13 programming languages. It is suited to multilingual text generation and research workflows that need an openly documented transformer model.

Delegate complete tasks like incident response, root cause analysis, alert triage, migrations, postmortem generation, and performance optimization without changing your workflow.

Canva is a free-to-use online graphic design tool. Use it to create social media posts, presentations, posters, videos, logos and more.

Describe your idea in plain words. Capacity asks the right questions, builds your app, and puts it online: accounts, payments, your own domain. Start free.

CLI to Chat with your AWS Cloud from Terminal using generative AI.

Anthropic's agentic coding tool for developers. Claude Code understands your codebase, edits files, runs commands, and helps you ship faster.

Even today's best Large Language Models (LLMs) still occasionally hallucinate incorrect answers that can undermine your business.

Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by 8M+ developers worldwide.

Cohere provides enterprise AI models and platform services for private, secure, and customizable business deployments. Teams use it to build applications that work with internal knowledge and organizational workflows.

Codeflash uses AI to automatically find the most optimized version of your Python code through benchmarking — while verifying it's correct.

CodeGeeX is an AI-based coding assistant, which can suggest code in the current or following lines. It is powered by a large-scale multilingual code generation model with 13 billion parameters, pretrained on a large code corpus of more than 20 programming…

AI-first pull request reviewer with context-aware feedback, line-by-line code suggestions, and real-time chat.

Qodo is an AI code review tool giving teams deep codebase context to move faster and improve code quality, with 15+ agentic workflows for IDEs, PRs and security.

An open-source AI coding assistant for connecting models to code editors and software-development workflows.

The Leading Multi-Agent Platform.

An AI coding environment with agents that can plan, edit, search, and build software tasks.

DALL·E 2 is an AI system that generates original images and artwork from natural-language descriptions. It combines concepts, attributes, and styles for creative image exploration, inpainting, outpainting, and image variations.

Devin is an AI software engineer for planning and executing complex development tasks, including migrations, PR review, documentation, and incident resolution. Engineering teams can connect it to workflow tools to automate multi-repo and recurring software work.

The AI mobile app designer that turns your ideas into stunning UI. Describe your app, get polished screens instantly. No Figma skills needed.

Google's AI coding assistant for code completion, generation, explanation, and developer workflow support.

Update: Ghostwriter is out now! In 2018 when we announced Multiplayer Mode, we said it's the most significant evolution of Replit to date. For the first...

An AI coding assistant for suggesting code, explaining codebases, writing tests, and accelerating development work.

Create agentic, context engineered AI systems using Haystack’s modular and customizable building blocks, built for real-world, production-ready applications.

Build and run AI workflows that can talk, act, and remember across channels. Hexabot combines conversations, actions, memory, MCP tools, and self-hosted control for real service operations.

Imagen is Google Research’s text-to-image diffusion system, built to turn written prompts into photorealistic images with strong language understanding. It is presented as a research model for studying high-fidelity image generation and image-text alignment.

An AI coding assistant integrated with JetBrains development tools for coding, explanation, and project work.

Keploy builds a Digital Twin of your production behavior — real API traffic, mocks, and dependencies — so every AI- or human-written change is verified in CI before it ships. Open source, zero code changes.

Build better AI systems with evals, RAG, agents, synthetic data, fine-tuning, and prompt optimization. Free app + open-source library.

Kilo is the open source AI coding agent for VS Code, JetBrains, CLI, and Cloud. Access 500+ models, bring your own keys at zero markup, and keep code private with local models.

Kiro helps developers and teams do their best work: turn prompts into executable specs, validate code correctness to find bugs unit tests miss, and build across large codebases with parallel agents that learn from every session.

LangChain provides the engineering platform and open source frameworks developers use to build, test, and deploy reliable AI agents.

Trace, evaluate, and improve AI agents with one open platform. Use production data to understand behavior, collaborate on fixes, and ship better quality at lower cost and latency.

Build controllable agents with LangGraph, our low-level agent orchestration framework.

LLaMA is Meta’s foundational language-model family for research and fine-tuning. Its smaller parameter sizes support text-generation experiments, responsible AI studies, and teams working with more limited computing resources.

LlamaParse is the world.

Language Model Query Language.

Uses text prompts plus freehand sketches to generate AI images matching a user’s intended composition—specifying object size, position, and orientation—aimed at artists, designers, and creators turning rough layouts into faithful visuals.

At Maxim AI, we are building the production infrastructure for AI. Maxim’s stack comprising gateway and governance, observability, and evals empowers AI teams to ship agents with the reliability and speed required for real-world use.

Self-updating documentation for startups, enterprises, and agents.

An AI cloud platform for developers who need access to models, inference services, and agent-building infrastructure.

Ollama is the easiest way to automate your work using open models, while keeping your data safe.

An open-source coding agent built for low-cost and open-weight models.

OpenAI API Platform gives developers access to frontier multimodal models for building agent workflows, grounded retrieval, and tool-using applications. It is intended for teams bringing AI capabilities into products and internal systems.

Learn how to use the OpenAI API to generate human-like responses to natural language prompts, analyze images with computer vision, use powerful built-in tools, and more.

Welcome to Portkey status page for real-time and historical data on system performance.

Meet OpenHands, the open-source, model-agnostic platform for cloud coding agents. Automate real engineering work securely and transparently. Build faster with full control.

Opik is an end-to-end AI observability platform designed to help developers test, ship, and continuously improve agentic systems.

OPT is Meta AI’s family of decoder-only language models, represented here by the 350M-parameter checkpoint. Developers and researchers can use it for text generation, downstream evaluation, and reproducible study of large language models.

Manage and create on-call schedules, sync oncalls with Slack usergroups, Jira and JSM on Slack, Opsgenie on Slack, and run incident response inside Slack…

PearAI is an open source AI code editor with powerful features like AI chat, PearAI Creator, and AI debugging to help you make what excites.

Democratize and productionize Gen AI across your entire org with Portkey.

Prediction Guard.

How Python does AI: agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

An AI code-quality platform for generating tests, reviewing changes, and improving software reliability.

Roomote is an AI engineering teammate that ships reviewable PRs — hosted by us in about two minutes, or self-hosted on your own infra. Single-tenant either way, source-available, bring any model. Solo dev or whole team.

Runcell is an AI agent for Jupyter notebooks that automates writing Python code, executing cells, debugging, and explaining data analysis results in real time.

Singlebase is an AI-native backend platform and Firebase alternative, combining document and vector databases, authentication, storage, and built-in AI services to power modern applications at scale. Build and scale backend + AI services. Singlebase.cloud…

An AI coding assistant for understanding codebases, generating code, and answering repository questions.

Stable Beluga 1 is a Stability AI instruction-following language model built by fine-tuning LLaMA 65B on an Orca-style dataset. It is intended for developers experimenting with English text generation through the Hugging Face Transformers ecosystem.

Stable Beluga 2 is Stability AI’s LLaMA 2 70B–based autoregressive language model, fine-tuned on an Orca-style dataset. It gives developers an open-weight option for instruction-led English text-generation experiments and prototyping.

Stable Diffusion v1-4 is a latent text-to-image model that generates or modifies images from written prompts. Researchers and creative developers use the checkpoint with Diffusers for generative-image experiments, artistic tools, and safety-focused evaluation.

Stenography automatically documents codebases through a VS Code extension and API that turn code into plain-English explanations. Developers can keep documentation current, request related resources, and surface explanations where they write code.

The fastest copilot. Supermaven uses a 1 million token context window to provide the highest quality code completions.

The fastest AI copilot for JetBrains. Write code 10x faster with intelligent autocomplete and an AI agent.

An AI code assistant for software teams that provides code completion and development support.

TensorZero builds open-source tools for production-grade LLM applications: LLM gateway, observability, optimization, evaluations, and experimentation.

TraeCode integrates seamlessly into your workflow, collaborating with you to maximize performance and efficiency.

The AI Toolkit for TypeScript, from the creators of Next.js.

We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary evaluation using GPT-4 as a judge shows Vicuna-13B achiev...

Infrastructure to build, measure, and interact with agents across your SDLC — so you ship more and spend less.

W&B Weave helps production agents learn and improve from real-world experience, so they can reach and maintain reliability.

Building the future of work, with Sauna.