Alternatives to Surfkit

Open-source Python framework for building AI web agents that turn plain-English objectives into Selenium or Playwright browser actions.

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

TabTin is an open-source team harness where you and multiple AI sub-agents share one task surface for code, docs and research.

Open-source agentic AI framework that runs autonomous agents with real terminal, file, and browser access on your own machine.

Run AI coding agents in isolated cloud sandboxes — locally on your Mac or delegated from Slack, Linear, and GitHub.

Zhipu GLM is a full-stack large-model platform with open-weights GLM-5.3 coding models, MaaS APIs and autonomous agents.

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

Open-source vision-driven GUI agent for natural-language end-to-end UI testing across web, mobile, and desktop

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

Open-source self-hosted AI assistant that drives a real browser, triages email, runs SEO analysis and publishes to WeChat and Twitter.

Stagehand is the open-source browser agent SDK that pairs Playwright-style APIs with Act, Extract, Observe and Agent primitives.

AgenticSeek is a fully local, open-source AI assistant that browses the web, writes and runs code, and plans multi-step tasks on your own machine.

Self-hosted layer that gives your AI coding agents shared memory, managed MCP tools, and cross-model audit.

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

Local-first memory layer for Claude Code and OpenCode that scores memories by whether they actually worked.

A persistent, file-based memory layer for coding agents that lives as a brain/ Markdown folder in your repo.

E2B spins up isolated Linux sandboxes per second so AI agents can run code, process data, and use tools without touching your host.

Naïve is agent infrastructure for autonomous companies — spend policy, real identity, and multi-agent orchestration in one committed config.

Vercel deploys web apps and AI agents from Git with preview URLs, a global CDN, sandboxed VMs, and one AI Gateway.

Loomal is a payments layer for agentic commerce — paywall an API or MCP tool and get paid per call in USDC on Base.

SWE-ReX is a runtime interface for sandboxed shell execution, letting AI agents run commands on any environment.

Rover runs multiple AI coding agents in parallel, each in its own isolated sandbox on your local machine.

Self-hosted autonomous AI agents that browse, run code, deploy apps, and make phone calls inside sandboxes you control.

Local-first memory layer that gives your AI coding agent a SQLite file it can recall from between sessions.

Dedalus Labs boots full Linux VMs for AI agents in under 50ms with per-second active-compute billing.

Gemini is Google's multimodal AI assistant for grounded search, drafting, and voice, video, and agentic tasks.

Run AI-generated code in secure, isolated Daytona sandboxes that spin up in under 90ms with per-second billing.

Sky is a natural language AI assistant for macOS that reads what's on your screen and acts inside the apps you already use.

Fly.io runs AI agent sandboxes on hardware-isolated Linux VMs called Sprites that checkpoint automatically and bill by the second.

Self-hosted AI agent with a browser UI, markdown memory on disk, and a cron scheduler that runs while you're offline.