Open-source alternatives to Cursor

claw-code

Rust CLI coding agent harness using Anthropic and OpenAI-compatible APIs

Claw Code is a Rust implementation of the `claw` command-line coding agent, built from source with cargo. It runs one-shot prompts or interactive sessions using an API key, and the docs cover local OpenAI-compatible servers such as Ollama, llama.cpp and vLLM. The README describes the repo as an agent-managed exhibit, not the production project, and points to LazyCodex and Gajae-Code for real work.

• no GPU
• Docker + Compose
• Needs Rust toolchain (cargo), LLM API key
• Models: Anthropic API, OpenAI-compatible APIs, Ollama, llama.cpp, vLLM

codewhale

Terminal coding agent in Rust that works with 40+ model providers

Codewhale is a terminal coding agent that reads a repository, edits files and runs shell commands until a task is done or it needs input. It supports more than 40 built-in providers, any OpenAI-compatible endpoint, and local models through Ollama, vLLM or SGLang, with DeepSeek as the default. It also has a headless exec mode, a local web UI, a PR review command and an ACP server for editors.

• GPU optional
• Docker
• Needs Git repository, Provider API key or local runtime (Ollama, vLLM, SGLang), bubblewrap (optional, Linux sandbox)
• Models: DeepSeek, Anthropic, OpenAI, Google, Mistral

deepseek-reasonix

Coding agent for terminal, desktop, browser and editors, with a DeepSeek preset

Reasonix is a Go coding agent that reads a project folder, edits files, and runs commands and tests, showing each step. It ships as a desktop app (Studio), a terminal UI, a local web interface via `reasonix web`, and an ACP backend for editors. Providers are declared in `reasonix.toml`; DeepSeek is a built-in preset and any OpenAI-compatible endpoint is a config entry.

• no GPU
• Needs Model provider API key, Go 1.25+ (build from source), Node 24+ and pnpm 10 (build Studio)
• Models: DeepSeek (preset), OpenAI-compatible endpoints, MCP servers

t3code

Desktop, web and mobile front end for controlling local coding agent CLIs

T3 Code is a control surface for coding agents already installed and authenticated on your machine: Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity. It runs a local server started with the `t3` command and is reached through a web app, an Electron desktop app, or iOS and Android apps for remote use. The README says the project is early and bugs are expected.

• no GPU
• Needs At least one of: Codex CLI, Claude Code, Cursor CLI, Grok Build CLI, OpenCode, Antigravity
• Models: Claude Code, Codex, Cursor, Grok Build, OpenCode

Archon

YAML workflow engine that runs AI coding agents through fixed dev steps

Archon lets you define development processes (plan, implement, validate, review, PR) as YAML workflows in `.archon/workflows/`, mixing bash nodes with AI nodes, loops and approval gates. Each run gets its own git worktree. It runs from a CLI, web UI, Slack, Telegram, Discord or GitHub webhooks, using Claude, Codex or Pi, and ships an `sdlc` workflow pack.

• no GPU
• Docker + Compose
• Needs Bun, Claude Code, GitHub CLI, SQLite or PostgreSQL
• Models: Claude, Codex, Pi

pi

Terminal coding agent with extensions, skills, and an SDK

Pi is a TypeScript coding agent CLI that runs in your project directory and connects to LLM providers through a login or API key. It is customized with extensions, skills, prompt templates and themes, shared as npm or git packages, and can be driven interactively, in print/JSON mode, over RPC, or through a TypeScript SDK. The monorepo also ships a multi-provider LLM API, an agent runtime and a terminal UI library.

• no GPU
• Needs Node.js 22.19+, LLM provider API key or subscription
• Models: OpenAI, Anthropic, Google

oh-my-openagent

Terminal coding agent with multi-model orchestration and git-backed memory

OmO installs a native `omo` command that runs a coding agent on senpi, a fork of pi. It supports sign-in to Claude, ChatGPT, Kimi and GLM subscriptions, a keyword (`ulw`, `mass ulw`) that fans a task out into a graph of parallel agents, and a memory layer stored as markdown in a git repository. Config lives in `~/.omo/omo.jsonc` with per-project overrides.

• Needs Model provider account or API keys
• Models: Claude, ChatGPT, Kimi, GLM

goose

Rust AI agent with desktop app, CLI and API, extended through MCP

goose is a general-purpose agent written in Rust that runs locally as a desktop app (macOS, Linux, Windows), a CLI, or an embeddable API. It connects to 15+ model providers, including Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure and Bedrock, and to 70+ extensions over the Model Context Protocol. It is hosted by the Agentic AI Foundation at the Linux Foundation.

• Docker
• Needs LLM provider API key or ACP-linked subscription
• Models: Anthropic, OpenAI, Google, Ollama, OpenRouter

opencode

Terminal-based AI coding agent with build and plan modes

OpenCode is a coding agent that runs in the terminal, with a beta desktop app, and works on your repository. It ships two built-in agents switched with Tab: a full-access build agent and a read-only plan agent that denies edits and asks before running bash. A general subagent handles multistep searches and can be called with @general.

openinterpreter

Terminal coding agent, a Codex fork tuned for low-cost models

Open Interpreter is a Rust fork of OpenAI's Codex that runs as a terminal coding agent. It can emulate other agent harnesses (claude-code, kimi-code, qwen-code, swe-agent and others) via /harness, so cheaper models are driven the way their providers recommend. It also runs as an ACP agent for editors and accepts the Codex exec protocol.

• Needs agent-browser, trycua
• Models: OpenAI-compatible Chat Completions providers, Kimi K3, DeepSeek, Z.AI GLM