AI IDE List

Obscura is an open-source Rust headless browser engine built for AI agents, web automation, and scraping. It exposes Chrome DevTools Protocol compatibility so existing Playwright and Puppeteer workflows can use it without depending on Chromium.

Browserbase is a complete browser-agent platform with managed browsers, hosted agents, Search and Fetch APIs, Runtime, Agent Identity, Model Gateway, observability, and the open-source Stagehand SDK and Browse CLI.

Steel is an open-source browser API for AI agents and apps, available as a managed cloud or self-hosted runtime with CDP sessions, profiles, credentials, proxies, CAPTCHA solving, browser tools, replays, and observability.

Hyperbrowser is cloud browser infrastructure for AI agents with managed Chrome sessions, stealth, proxies, CAPTCHA solving, profiles, recordings, web data APIs, sandboxes, MCP, and several hosted browser-agent options.

Kernel is fast, open-source browser infrastructure for web agents, offering isolated Chromium sessions, CDP and WebDriver BiDi control, managed auth, stealth, GPU acceleration, telemetry, replays, pools, and colocated agent compute.

Anchor Browser provides secure cloud computer environments for AI agents, including managed browsers, natural-language tasks, deterministic workflows, OmniConnect authentication, stealth, and enterprise deployment options.

Notte is a unified browser platform for AI agents with cloud sessions, browser agents, serverless browser functions, profiles, vaults, personas, proxies, replays, and observability.

Browser Use is an MIT-licensed Python framework and managed cloud platform that lets AI agents navigate websites, click, type, extract data, and complete browser tasks.

APIMart is an OpenAI-compatible AI API gateway that unifies access, billing, routing, and monitoring across language, image, video, and audio models through one account and API key.

Port22 is an iPhone remote control for Claude Code, Codex, and OpenCode sessions running on a Mac, letting developers read transcripts, respond, and handle permission prompts away from the desk.

Skydive turns a coding setup into a persistent cloud agent by importing instructions, skills, MCP servers, and secrets from tools such as Claude Code, Cursor, and Codex into a remote workspace.

Berd is Block's open-source desktop agent workspace for organizing projects, chats, files, models, tools, skills, and subagent activity in a model-neutral environment powered by Goose.

Slack Code adds project code channels where developers and coding agents can collaborate around diffs, previews, approvals, feedback, canvases, and an auditable history inside Slack.

Cindy is an open-source agent workspace that runs Claude Code, Codex, and Pi while preserving project workspaces, memory, skills, tools, and context when users switch harnesses or models.

GitNexus by Akon Labs builds a knowledge graph of code dependencies, call paths, execution flows, and cross-repository context, then exposes that intelligence to coding agents through MCP.

Hugging Face is an AI collaboration and developer platform for discovering, versioning, evaluating, fine-tuning, and deploying models, datasets, and applications through the Hub, open-source libraries, Spaces, Jobs, inference providers, and dedicated endpoints.

Anthropic Console is the developer control plane for accessing the Claude API, creating API keys, managing organizations and billing, experimenting in Workbench, generating prompts, and reviewing usage and costs.

LangChainGo is a community-maintained Go implementation of LangChain concepts for building LLM applications with agents, chains, tools, prompts, memory, retrievers, vector stores, and multiple model providers.

Guidance is an MIT-licensed language for controlling large language model generation with regular expressions, context-free grammars, control flow, tool use, and efficient interleaving of generation and application logic.

Instructor is an open-source library for extracting structured, validated data from LLM responses with typed schemas, automatic retries, streaming, and support for many model providers across multiple programming languages.

Cerebrium is a serverless AI infrastructure platform for deploying GPU and CPU workloads such as voice agents, model APIs, video pipelines, and custom inference with per-second compute billing and production observability.

Cerebras Inference is an ultra-fast hosted model API for coding, reasoning, voice, automation, and agentic applications, with OpenAI-compatible endpoints, official SDKs, self-serve credits, and enterprise capacity.

Cloud Run is Google Cloud’s fully managed application platform for deploying containers, source code, APIs, jobs, AI agents, MCP servers, and inference workloads with automatic scaling and pay-per-use billing.

OpenRouter provides one OpenAI-compatible API for routing requests across hundreds of models and inference providers. It is useful for coding agents and agent applications that need model choice, fallbacks, unified billing, and rapid comparison without integrating each provider separately.