
The AI coding agent for building ambitious software
The AI coding agent for building ambitious software
Refact.ai: An open-source AI coding assistant supporting self-hosted models, offering greater privacy than cloud-locked extensions. CodeGPT records 170,064 monthly visits with -19% month-over-month growth and Freemium, Paid, Contact for Pricing pricing. Refact.ai records 40,171 monthly visits with -20.8% growth and Freemium pricing.

Open-source, self-hosted AI coding agent that codes like you
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | codegpt.co | refact.ai |
| Pricing Model | Freemium, Paid, Contact for Pricing | Freemium |
| Monthly Visits | 170.06K (170,064) | 40.17K (40,171) |
| MoM Traffic Delta | -39.85K (-19%) | -10.53K (-20.8%) |
| Primary Market & Share | 🇮🇳 India (13.6%) | 🇺🇸 United States (18.4%) |
| Direct Visits / mo | 92.07K | 5.72K |
| User Rating | 4.3 | 4.4 |
| Supported Platforms | Website | Website |

AI coding agent for VS Code, JetBrains and Visual Studio with bring-your-own-key model freedom
Connect Claude, GPT, Gemini, Grok or local Ollama/LM Studio models with your own API keys, or use CodeGPT credits, and switch models per task without moving your code.
The agent reads your codebase, proposes a plan you can edit, and writes code only after you approve each step, keeping you in control of every change.
Watch which files are read, which options are weighed and which edits are suggested, with live tracking of context usage and no hidden limits.
Bridge the agent to external APIs, documentation and databases through MCP, and define project rules so generated code follows your standards.

Open-source, self-hosted AI coding agent that codes like you
A task-driven agent that plans work, searches your repository for context and executes changes step by step, connecting to GitHub, databases and CI/CD.
In-IDE chat for asking, editing, debugging and generating code in natural language, plus fast multi-line autocompletion powered by RAG over your project.
Deploy on-premise or run the open-source version to keep your code private and fully under your own control.
Pick from leading LLMs or bring your own API key, and fine-tune the agent on your company's coding style and stack.

The AI coding agent for building ambitious software
The AI coding agent for building ambitious software
A comprehensive agentic development suite by Google for running parallel coding agents, but requires a separate environment.
A comprehensive agentic development suite by Google for running parallel coding agents, but requires a separate environment.

Free / Open-sourceWrite code with precision, hand bigger jobs to agents, and keep working from anywhere
Free / Open-sourceWrite code with precision, hand bigger jobs to agents, and keep working from anywhere
An agentic coding platform that ships real software
A spec-driven AI IDE from AWS that plans and verifies engineering work, but requires switching editors.
A spec-driven AI IDE from AWS that plans and verifies engineering work, but requires switching editors.

The coding agent that learns your coding taste
The coding agent that learns your coding taste
Free / Open-sourceA minimal, extensible terminal coding agent you can reshape
Free / Open-sourceA minimal, extensible terminal coding agent you can reshape

Free / Open-sourceOpen-source control plane for orchestrating coding agents

AI code review, PR triage, and security monitoring for fast-moving teams
AI code review, PR triage, and security monitoring for fast-moving teams
An AI-powered development environment that plans and tests code projects, but operates as a standalone IDE.
An AI-powered development environment that plans and tests code projects, but operates as a standalone IDE.
Baidu's ERNIE-powered AI coding partner for your IDE

Provides enterprise-grade context engines for large codebases, though less modular for swapping arbitrary model providers.
Provides enterprise-grade context engines for large codebases, though less modular for swapping arbitrary model providers.