Alternatives to Random Labs

Claude Code is Anthropic's agentic coding assistant for multi-file repo work from the terminal, IDE, browser, or cloud.

OpenAI Codex is a cloud coding agent that runs parallel software engineering tasks in isolated sandboxes

Open-source terminal coding agent that reads your repo, edits files, runs commands, and uses the model you choose.

Openclaude is an open-source terminal coding agent CLI that runs any model, from OpenAI and Gemini to local Ollama, inside your repo.

Ellipsis runs Claude Code and Codex coding agents in managed cloud sandboxes, configured in YAML in your repo

Open Interpreter is an open-source terminal coding agent that reads files, edits code, and runs shell commands from plain English.

Open-source coding agent that edits files and runs bash commands in your IDE, terminal, or desktop app.

WeSight is an open-source desktop workspace that runs Claude Code, Codex and other CLI coding agents side by side.

OpenCode is an open-source AI coding agent that runs in your terminal, IDE, or desktop and connects to any LLM.

Hermes IDE is a desktop console that runs every coding agent side by side in its own terminal, on its own git branch.

Herm is a containerized coding agent that runs every terminal session in its own sandbox, so it can act without touching your host

Terax is a terminal-first AI-native dev workspace with Vim editing, agentic AI coding agents, and live web preview in a 7 MB app

ForgeCode runs AI coding agents straight from your ZSH prompt — an open-source terminal coding harness.

Localforge is a free, MIT-licensed desktop coding agent GUI that runs autonomous multi-file code edits in your own repo with any LLM.

Poolside builds open-weight agentic coding models — Laguna S 2.1 (118B) and Laguna XS 2.1 (33B) — plus the runtime that runs them.

OpenHands runs autonomous coding agents that review PRs, fix CI failures, and open pull requests from GitHub, Slack, Jira, or Linear.

Kiro turns prompts into validated specs, then ships them with parallel AI coding agents

Fimo runs autonomous website agents and a visual AI CMS on your own Git repo, with managed hosting included.

Warp runs fleets of cloud coding agents across your SDLC, defined in code and scored on every run.

JetBrains' AI coding agent for the terminal, JetBrains IDEs, GitHub, and GitLab — any model you bring.

Glamourous agentic coding in your terminal: bring your own LLM, LSP context and MCP tools, swap models mid-session.

Open-weight agentic coding models — Laguna S 2.1 (118B) for long-horizon agent work and Laguna XS 2.1 (33B) to run on-device.

Pi Coding Agent is a free, MIT-licensed terminal coding agent harness you extend with TypeScript extensions, skills, and Pi packages.

Qoder is an agentic coding platform that runs a full plan-execute-verify agent loop across IDE, CLI, JetBrains, and mobile.

Terminal coding agent with hash-anchored edits and the IDE wired straight into your shell

OpenSpec is an open-source spec-driven development framework that keeps AI coding agents building the right thing, with verify and archive

DeerFlow is an open-source SuperAgent harness that runs deep research, coding, and creation tasks in a persistent Docker sandbox.

Devin Desktop runs a fleet of local and cloud coding agents from one agent command center.

Capy orchestrates a fleet of parallel cloud coding agents across Slack, GitHub, and Linear.

Xiaomi's terminal AI coding agent: open-weight MiMo-V2-Flash, unlimited-context memory, curl install, no login.