Alternatives to Ref Tools

Multiplayer coding agent IDE and cloud that runs a six-phase QRSPI workflow so teams review design before 2,000 lines of code land.

Cosine Genie is a sovereign coding agent that writes production-grade code with Lumen models post-trained on real engineering code.

Open-source platform for autonomous coding agents that fix bugs, review PRs, and automate engineering workflows.

Claude Code is Anthropic's agentic coding assistant that plans, edits, and runs commands across your repo from the terminal, IDE, or browser.

Open-source autonomous AI coding agent that plans, executes, and deploys tasks inside VS Code and JetBrains IDEs.

Open-source AI + no-code platform where coding agents and AI employees build and run business systems on production-proven infrastructure.

Cursor for iOS is the iPhone and iPad app for launching AI coding agents, reviewing their work via video and screenshots, and merging PRs from your phone.

Paseo is a self-hosted control plane that runs Claude Code, Codex, Copilot and 30+ other coding agents from your phone, desktop, browser or CLI.

Linear is a product development system that embeds AI agents into planning, triage, coding, and code review for engineering teams.

Cognition builds Devin, an autonomous AI software engineer that plans, codes, tests, and ships merge-ready pull requests inside your

Roo Code is a pre-launch multi-agent AI coding assistant for VS Code, currently collecting email signups on a landing page only

Define cloud coding agents in environment.yaml, deploy them by merging a PR, and run Claude Code or Codex with scoped permissions and hard spend caps.

SmolAgents is Hugging Face's Apache-2.0 Python library for building agents that write their actions as executable code.

Open platform for running fleets of cloud coding agents across your SDLC, with an agentic terminal and a CLI agent that works anywhere

GitLab Duo is GitLab's agentic AI layer, adding specialized AI agents, code review, and policy-governed automation directly into DevSecOps workflows.

Devin is Cognition's autonomous AI software engineer that plans, codes, tests, and ships mergeable pull requests.

Cursor is your coding agent for building ambitious software — plan, build, test and ship with AI agents across IDE, CLI, Slack and cloud.

Agentic coding platform where one agent core drives an IDE, CLI, JetBrains plugin, mobile app, SDK, and cloud agents.

Coder is a self-hosted platform for cloud development environments that governs the AI coding agents and LLM traffic running inside them.

Open-source desktop workspace that runs Claude Code, Codex, OpenClaw, and other CLI coding agents side by side with per-task model routing.

Desktop AI code editor (VS Code fork) with a router that auto-selects the top-scoring coding model and an autonomous coding agent.

Devin Desktop (formerly Windsurf Editor) is an IDE built around running fleets of local and cloud coding agents from one surface.

Capy orchestrates fleets of cloud coding agents inside Slack, GitHub, and Linear, with unlimited members on every plan.

Terminal-first AI dev workspace: Vim editor, agents, Git, and live web preview in a 7 MB Tauri app

Godcoder is a local-first, open-source AI coding agent desktop app that writes its own harness and keeps your code on your machine.

Foreman is an open-source Textual TUI that supervises headless Claude Code agents through a gated plan → ADR/PRD → issues → TDD → e2e delivery pipeline.

Userdoc turns ideas, code, and designs into structured software specs that both people and AI coding agents can read.

Kanwas is a shared context board where product teams and their AI agents compound context into execution-ready deliverables.

Spec-driven product and feature planning that turns your idea into build-ready work for AI coding agents.

Open-weight agentic coding models — Laguna XS 2.1 (33B) and Laguna S 2.1 (118B) — built for code that cannot leave your security boundary.