Alternatives to Stagehand

Open-source MCP server that gives coding agents live Chrome DevTools access for debugging, automation, and performance traces.

Open-source Python framework for building AI web agents that turn natural-language objectives into browser actions.

Open Interpreter is an open-source terminal agent that turns plain-English requests into real file edits and shell commands on your machine.

Million open-sources React Doctor (15k stars) and React Scan (22k stars), and is building ReactBench to check AI-written React before it ships.

Code-first browser automation platform where an AI agent builds and maintains scrapers, crawlers, and RPA workflows as production-ready Playwright code.

Open-source Rust CLI that measures a released command-line binary as a black box and emits evidence-backed command shape files agent harnesses can route on.

TabTin is an open-source team harness where humans and AI sub-agents share one task surface for code, docs, spreadsheets and browser

Closed-loop QA platform that turns real mobile bugs into regression tests your coding agents can run.

Open-source npm package that plugs 60 specialized QE agents and 76 skills into your coding agent over MCP.

Open-source agentic AI framework that runs autonomous agents on your own machine with Docker sandboxing and any LLM provider.

AI session replay that watches every session, triages the bugs it finds, and opens pull requests to fix them.

Open-source computer-use agent orchestrator that launches GUI agents locally, in Docker, or on any cloud.

Open-source browser extension that turns Chrome or Firefox into a local AI agent workstation with your own tabs, sessions, and model keys.

Always-on Python tracer that records runtime data and generates working Django integration tests.

OpenAgents is an Apache-2.0 platform for language agents that analyze data, call 200+ plugins and browse the web.

Zhipu GLM (Z.ai) ships the open-weights GLM-5.3 family, full-modality MaaS APIs, and autonomous agents like AutoGLM and GLM-PC.

Cloud browser sessions, sandboxes, and AI agents for web scraping and agentic automation.

Open-source vision-driven GUI agent for cross-platform end-to-end UI testing in natural language

Free, open-source AI code assistant plugin for JetBrains IDEs with spec-driven development and agent mode

Open-source, self-hosted AI agent that plans tasks, runs tools, and grows its own memory.

Open-source self-hosted AI assistant that actually does the work — browser, email, calendar, code, SEO, and multi-platform publishing.

Playwright cloud companion that records CI runs, detects flaky tests, and serves failure context to humans and AI agents over MCP.

AI platform for chip verification that finds bugs on 100GB+ waveforms, triages nightly regressions, and speeds UVM bring-up before tape-out.

TestDriver runs AI UI testing on every GitHub pull request — black-box E2E tests that self-heal.

BrowserBook is a developer IDE for building deterministic browser automations — a Jupyter-style notebook, an inline browser, and an AI coding assistant in one

ManyPI turns a sentence about your ideal customer into verified leads, cold email sequences, and a CRM in one workspace.

An open-source autonomous AI companion that learns your habits and drives your desktop, browser and APIs for you.

Hosted crawling and extraction API that turns any URL into clean markdown, HTML, or structured JSON for AI agents and RAG pipelines.

Runtime verification for Java and Kotlin: capture real traces, diff PR behavior, and replay them as JUnit regression tests.

Open benchmark from OpenAI and Paradigm that tests whether AI agents can find, patch, and exploit high-severity smart contract bugs