A checked list of AI coding tools and agents.
120 entries. Tap one for the details.
- All
- Editors
- CLI agents
- Cloud agents
- Code review
- App builders
- Local models
- Picks first
- A to Z
- By category
120
-
AI features inside Appsmith for building internal tools. Only listed if there is a clear, current product page.
Web, Self-hosted
-
A browser tool that turns a prompt into a working web app you can iterate on and export.
Web
-
A workspace for building internal apps with an agent that writes the front end and the Python back end in one place.
Web
-
A local, open-source app builder that runs on your machine, so the prompt-to-app loop does not have to leave your computer.
macOS, Windows, Linux
Editor's pick
-
An agent that builds and deploys an application from a brief, with the source left in a repository.
Web
-
Google's browser workspace, grown out of Project IDX, where Gemini can help you scaffold, edit and preview a full-stack or mobile app.
Web
Editor's pick
-
An open-source, local visual editor for React apps that can also take a prompt, sitting closer to the code than a typical website builder.
macOS, Windows, Linux
-
An agent that writes a web app and its tests from a prompt, with a focus on keeping the generated code in a real repository you can run.
VS Code, Web
-
Reflex's prompt-to-app path for building a Python web app, kept only if the official build product is clearly offered.
Web
-
A prompt-to-app builder that produces a real codebase for web apps, aimed at people who still want to own the repo.
Web
-
An open-source internal-tools builder with AI help for generating queries and UI. Only listed if the AI product is clearly offered.
Web, Self-hosted
-
An open-source terminal pair-programmer that maps your repo, makes edits and commits each change, and can talk to hosted or local models.
macOS, Linux, Windows
Editor's pick
-
The terminal interface for Amazon Q Developer. Like the IDE plugins, it is on a path toward Kiro.
macOS, Linux, Windows
-
Sourcegraph's coding agent and environment, with local and remote 'orbs' so an agent can keep working after you close the laptop.
CLI, Web, Editors
Editor's pick
-
Anthropic's terminal agent for long-running, multi-file work: it plans, edits, runs commands and can use subagents and hooks in a repo.
macOS, Linux, Windows
Editor's pick
-
OpenAI's coding agent, available as a CLI and as a cloud workspace, for repository-scale tasks on top of OpenAI's models.
CLI, Web
Editor's pick
-
A command-line way to run Cursor's agent over a project, for people who want the same model loop outside the editor window.
macOS, Linux, Windows
-
Cognition's command-line client for Devin, so the same cloud or local agent can be driven from a terminal.
macOS, Linux, Windows
-
Google's open-source terminal agent, with a very large context window and access to Gemini for repository tasks from the shell.
macOS, Linux, Windows
-
GitHub's command-line interface for Copilot, for asking questions and getting help with shell and repository tasks from the terminal.
macOS, Linux, Windows
-
A small open-source tool that turns a GitHub URL into a clean text digest for a model prompt.
Web, CLI
-
An open-source desktop and CLI agent, started at Block and now under the Agentic AI Foundation, that can edit, run commands and use MCP extensions with the model you bring.
macOS, Linux, Windows
Editor's pick
-
The command-line side of Amazon's Kiro environment, for agentic coding in the terminal with the same steering files and hooks as the IDE.
macOS, Linux, Windows
-
A smaller, simpler companion to SWE-agent, for running an issue-fixing loop with fewer moving parts.
Linux, macOS
-
A local agent that can run code on your machine from a natural-language prompt, in a chat-like terminal session.
macOS, Linux, Windows
-
An open-source terminal coding agent that can run in a TUI or inside editors that speak the Agent Client Protocol.
macOS, Linux, Windows
-
A terminal agent that builds a plan first, then applies it in a sandboxed workspace, with a strong emphasis on reviewing each step.
macOS, Linux, Windows
-
An open-source packer that turns a repository into a single file a coding model can read.
CLI
-
A tool for packing a repository into a prompt you can send to a model, useful when you are driving an agent by hand.
macOS
-
An open-source agent from Princeton's NLP group that uses an agent-computer interface to fix GitHub issues in a repository.
Linux, macOS
-
Cursor's hosted agents that keep working on a task in the cloud and bring a branch or pull request back into the editor.
Web, Cursor
-
Cognition's cloud software engineer: you hand it a ticket and it works on its own machine, then comes back with a pull request and a walkthrough.
Web, Slack, GitHub
Editor's pick
-
An agent platform whose 'Droids' take on planning, implementation, review and tests across the command line, chat and issue trackers.
CLI, Web, Slack, GitHub
-
A GitHub-hosted agent that can be assigned an issue, work in the background and open a pull request for you to review.
GitHub
-
A research lab building long-context coding models and an assistant for large repositories.
Web
-
An open-source software-engineer agent you can run yourself or use as a hosted service, for end-to-end repository tasks.
Self-hosted, Cloud
Editor's pick
-
A company building its own coding models and an assistant aimed at enterprises that want to run them in their own environment.
Enterprise
-
Anthropic's official GitHub Action for running Claude Code on a pull request, so the same agent that edits locally can also review or implement in CI.
GitHub
-
An automated code-quality platform that comments on pull requests and has added AI help for fixing and explaining issues.
GitHub, GitLab, Bitbucket
-
A review product that also scans for quality and security issues, aimed at teams that want one bot on the pull request.
GitHub, GitLab, Bitbucket
-
An AI reviewer that comments on pull requests across GitHub, GitLab, Bitbucket and Azure DevOps, with one-click fixes and a free path for public repositories.
GitHub, GitLab, Bitbucket, Azure DevOps
Editor's pick
-
An AI pull-request reviewer that focuses on high-signal comments and quick setup on GitHub.
GitHub
-
Cursor's pull-request reviewer, aimed at finding bugs and handing a fix back to the agents a team already uses in Cursor.
GitHub, Cursor
-
A static analysis platform with automated fixes and, on recent plans, AI-assisted explanations of the issues it finds.
GitHub, GitLab, Bitbucket
-
Cognition's reviewer for diffs and pull requests, including a mode you can point at a PR link without a full install.
GitHub, GitLab
-
A usage-priced review and fix agent for GitHub, with an option to run the reviewer inside your own AWS account.
GitHub
-
GitHub's built-in Copilot reviewer, available on pull requests for teams already on a paid Copilot plan.
GitHub
-
A stacked-pull-request workflow for GitHub, with a built-in AI reviewer that sits in the same inbox as the stack.
GitHub
-
A pull-request reviewer that indexes the whole repository so a comment can point at a caller or dependency far from the diff.
GitHub, GitLab, Bitbucket
Editor's pick
-
An AI reviewer used in teaching and in teams, leaving explanations on pull requests rather than only a pass/fail score.
GitHub
-
Qodo's open-source review bot (MIT) that you run with your own model keys on GitHub, GitLab, Bitbucket, Azure DevOps or Gitea.
GitHub, GitLab, Bitbucket, Azure DevOps, Gitea
-
A multi-agent review and test platform, formerly Codium, with team rules, generated tests and an enterprise option you can run yourself.
GitHub, GitLab, Bitbucket, Azure DevOps, IDE
-
A rule-based code scanner with an assistant that can help write rules and explain findings on a pull request.
GitHub, GitLab, CLI
-
Snyk's code scanner, built on the earlier DeepCode engine, for finding security issues in a pull request or an IDE.
GitHub, GitLab, Bitbucket, IDE
-
A quality-gate scanner with AI help for understanding and fixing issues, used as a merge gate in many teams.
GitHub, GitLab, Bitbucket, Azure DevOps, Self-hosted
-
An automated reviewer and in-editor refactoring assistant, well known for Python and now used more widely on pull requests.
GitHub, VS Code, JetBrains
-
A team assistant that answers questions about a codebase and can help on pull requests, using the team's own repos and docs.
Slack, GitHub, Web
-
A pull-request summariser and reviewer. Only kept if the official site is still serving the product.
GitHub
-
An open-source AI editor from CodeStory. Only listed if the official site is still live.
macOS, Windows, Linux
-
AWS's earlier IDE assistant. New sign-ups have stopped and AWS is moving people to Kiro, with existing access running until 30 April 2027.
VS Code, JetBrains, Visual Studio, Eclipse
-
Gemini built into Android Studio for explaining, generating and iterating on Android code and layouts.
Android Studio
-
An assistant for generating, explaining and testing code inside VS Code, JetBrains and a web app.
VS Code, JetBrains, Web
-
An assistant built for large existing codebases, with a context engine and a team-oriented editor integration.
VS Code, JetBrains
-
A Neovim plugin that puts an AI sidebar and inline edits next to your buffers, with a choice of model providers.
Neovim
-
A coding assistant and pull-request reviewer for GitHub, GitLab and Bitbucket, with an IDE extension and a self-hosted option.
VS Code, JetBrains, GitHub
-
A coding assistant and search product with an editor extension, a web app and a focus on looking up existing code.
VS Code, Web
-
An open-source VS Code agent with plan and act modes that can edit files, run terminal commands and use MCP tools, billed only through the model you bring.
VS Code
Editor's pick
-
A Neovim plugin for chat, inline assist and agent-style workflows, designed to feel like a native editor feature.
Neovim
-
A coding model and assistant from Tsinghua's KEG lab, with editor plugins and an open model family.
VS Code, JetBrains
-
A VS Code and JetBrains assistant that connects to several model providers for chat, edits and repository questions.
VS Code, JetBrains
-
Sourcegraph's coding assistant, using the company's code intelligence to answer questions and edit across large repositories.
VS Code, JetBrains, Web
-
An open-source extension for VS Code and JetBrains that lets you bring your own model, including local ones, for chat, edit and autocomplete.
VS Code, JetBrains
Editor's pick
-
An editor built around an agent that can edit several files, run commands and show you the diff, on top of a VS Code foundation.
macOS, Windows, Linux
Editor's pick
-
The editor formerly sold as Windsurf, now a Cognition IDE with a command centre for local and cloud agents, still compatible with VS Code extensions.
macOS, Windows, Linux
Editor's pick
-
A free coding assistant and autocomplete plugin from Fitten Tech, available for several editors.
VS Code, JetBrains
-
Google's coding assistant for editors and Cloud, using Gemini for completions, chat and larger repository-aware edits.
VS Code, JetBrains, Cloud Workstations
-
GitHub's coding assistant, with inline completions and chat inside VS Code, JetBrains, Neovim, Visual Studio and GitHub itself.
VS Code, JetBrains, Neovim, Visual Studio
Editor's pick
-
GitLab's built-in AI for suggestions, chat and merge request review, including on self-managed GitLab.
GitLab, VS Code, JetBrains
-
The official AI assistant inside IntelliJ IDEA, PyCharm, WebStorm and the rest of the JetBrains family, for completion, chat and in-editor edits.
IntelliJ, PyCharm, WebStorm, Rider
-
JetBrains' coding agent that can plan and apply changes across a project inside the JetBrains IDEs.
JetBrains IDEs
-
An open-source VS Code coding agent in the same family as Cline and Roo, if the official page is still live.
VS Code
-
Amazon's agentic IDE and CLI for spec-driven work, built as the successor to Amazon Q Developer, with hooks, steering files and custom subagents.
macOS, Windows, Linux
Editor's pick
-
A desktop workspace that saves snippets and context from your tools and offers an on-device or cloud assistant over that memory.
macOS, Windows, Linux
-
An open-source VS Code coding agent, started as a Cline fork, with custom modes and a strong focus on giving the agent controlled access to your repo.
VS Code
-
A fast completion plugin that was later acquired; only listed if the official site still serves a product page.
VS Code
-
A self-hosted coding assistant that serves completions from models you run, with editors talking to a local server.
Self-hosted, VS Code, JetBrains, Vim
-
A long-running completion assistant that can run fully self-hosted, aimed at teams that need the model to stay on their own network.
VS Code, JetBrains, Vim, Eclipse
-
AI features in the Eclipse Theia platform, so you can add an assistant to a custom, open-source IDE.
Theia
-
ByteDance's free AI-first editor, with a builder agent and a familiar VS Code-like workspace.
macOS, Windows, Linux
-
An open-source editor fork that keeps AI features local or on the model of your choice, as an alternative to hosted AI IDEs.
macOS, Windows, Linux
-
Visual Studio Code's own agent mode, built on GitHub Copilot, for multi-step edits and terminal work inside the stock editor.
VS Code
-
A modern terminal with a built-in agent that can run commands, edit files and walk through a repo without leaving the shell.
macOS, Windows, Linux
-
Apple's coding assistant built into Xcode, for completions, explanations and changes in Swift and Apple platforms.
Xcode
-
A fast native editor with built-in AI completions and an agent panel, written in Rust and designed for low latency.
macOS, Windows, Linux
Editor's pick
-
NVIDIA's desktop demo app for running local models on GeForce RTX GPUs, including some coding use.
Windows
-
Meta's open code-model family, still a common local baseline even as newer models have passed it on many benches.
Local
-
Google's open Gemma variant trained for code completion and generation, meant to be run locally or through a host.
Local
-
Mistral's family of models trained for code, available through Mistral's API and as weights you can run locally.
API, Local
-
DeepSeek's code-model family, including open weights that people run locally and the hosted models used by many coding agents.
Local, API
-
Mistral's agentic coding model family, aimed at repository tasks and available to run or call through Mistral.
API, Local
-
Docker's local model runner, so a coding tool can call a model packaged and served through Docker Desktop.
macOS, Windows, Linux
-
Microsoft's local runtime for running foundry-hosted models on a Windows or Mac machine, with an API that tools can call.
Windows, macOS
-
Nomic's desktop app and runtime for running local models with a simple installer, including a local API.
macOS, Windows, Linux
-
IBM's open Granite models for code, released for local and enterprise use with a relatively permissive licence.
Local, API
-
An open-source desktop app for running local models offline, with a ChatGPT-like interface and an OpenAI-compatible local server.
macOS, Windows, Linux
-
The widely used C/C++ runtime for running Llama-family and other models locally, including on CPUs and Apple silicon.
macOS, Linux, Windows
-
Mozilla's single-file format for distributing and running a local model: one executable that starts a server on your machine.
macOS, Linux, Windows
-
A desktop app for downloading and running local models, with a chat UI and a local server that coding tools can point at.
macOS, Windows, Linux
Editor's pick
-
A self-hosted, OpenAI-compatible API that can serve local models, including for coding tools that expect an API endpoint.
Linux, Docker
-
Apple's array framework for running models efficiently on Apple silicon, with mlx-lm used to serve local code models on a Mac.
macOS
-
The most common way to run open models on a laptop, including several code models, from a single command-line tool and a local API.
macOS, Linux, Windows
Editor's pick
-
A self-hosted chat UI that talks to Ollama and other local runtimes, often used as the front end for a private code model.
Self-hosted
-
Alibaba's open code-model family (Qwen2.5-Coder and later), widely run locally through Ollama, LM Studio and llama.cpp.
Local, API
-
A fast open-source runtime for serving large models, used as a local or private backend for agents.
Linux
-
An open code model from the BigCode project (ServiceNow and Hugging Face), trained on The Stack and released for local use.
Local
-
Hugging Face's server for deploying models, often used to host a private code model for an editor or agent.
Linux
-
A widely used local web UI for running and serving models, including code models, on your own hardware.
Windows, Linux, macOS
-
A toolkit for fine-tuning local models quickly, including code models, on a single GPU.
Linux, Windows
-
A high-throughput runtime for serving large models on your own GPUs, often used as the local or private backend for coding agents.
Linux
-
01.AI's open code-model family, available as weights for local inference.
Local
Nothing matches that. Try another word, or suggest a tool.
Suggest a tool
If an AI coding tool is missing, send the name and a link. We only add it after checking the official page.
A note when the list grows
Occasional email when we add a batch of tools worth opening. No ads, and we never sell the address.