Devin
FreemiumDevin is a cloud coding agent that takes a task, works through it in its own virtual machine, and opens a pull request when it finishes. It runs in the cloud or on your machine, can start Windows, Mac, or Linux environments, tests changes in a browser, and records what it did. Large jobs split across parallel agents, and sessions continue after you close your laptop. It connects to GitHub, GitLab, Bitbucket, Slack, Jira, and Linear, and offers an API plus a generated repository wiki. Paid plans meter usage with daily and weekly quotas instead of charging per seat.
Key features
- Cloud or local agent sessions with parallel execution
- Runs Windows, macOS, and Linux virtual machines and tests in a browser
- Opens pull requests and records its test runs
- Integrations with GitHub, GitLab, Bitbucket, Slack, Jira, and Linear
- Devin API and a generated repository wiki
Reviews
No reviews yet — be the first!
Log in to leave a review.
Related tools
Tools similar to this one — same category or shared tags.
Make
Make is a visual automation platform where you connect apps as modules on a canvas and pass data between them. A scenario can branch, filter, iterate over lists and call an HTTP endpoint, so one tool covers simple app-to-app syncs and longer multi-step processes. It connects to more than 3,000 apps, includes an MCP server, and offers AI agents plus a natural-language builder that turns a description into a working scenario. Pricing runs on credits, where each module action consumes one, and plans differ in execution frequency, log retention and priority execution.
n8n
n8n is a workflow automation tool you can run in the cloud or host yourself. Workflows are built on a visual canvas with more than 1,000 nodes, and each run counts as one execution no matter how many steps it contains. The AI agent node, MCP server trigger and chat hosting place language models inside ordinary business automations, connected to databases, CRMs and internal APIs. Code steps support JavaScript and Python when the visual builder runs out of room. The Community Edition is free to self-host, and cloud plans are priced by monthly executions.
Zed
Zed is an open-source code editor built for speed, with a native interface and GPU-accelerated rendering. It includes an agent panel that can read your project, edit files, and run commands, plus edit predictions that suggest the next change as you type. Zed connects to hosted models through a Pro subscription or to your own keys from Anthropic, OpenAI, Google, Bedrock, Ollama, and other providers. It also runs external agents such as Claude Agent and Codex CLI through the Agent Client Protocol. Multiplayer editing lets several developers share one workspace in real time.
Warp
Warp is a terminal built for coding agents, available as a desktop app and a command-line agent. You can run its agent in any terminal, launch cloud agents that work on a repository without your machine, and review what they changed. The terminal keeps command history, blocks, and workflows in a searchable drive, and indexes your codebase so the agent can find relevant files. It supports frontier and open-weight models, or you can bring your own API keys and inference endpoint. Paid plans include a monthly pool of agent usage at API rates, with add-on spending controls.
Replit
Replit is a browser-based development platform where an agent builds apps and websites from a plain-language description. You start with a prompt or the design canvas, then edit the generated code in a cloud IDE. The Agent writes full-stack code, and Replit provides authentication, a database, object storage, hosting, and monitoring without separate setup. More than 100 integrations connect services such as Stripe, OpenAI, and Google Workspace, and projects publish to a public URL. The free Starter plan includes daily Agent credits and one published app; Core adds fuller builds, more storage, and removes the Replit badge.
Kiro
Kiro is an agentic IDE from AWS that turns a prompt into a written specification before it writes code. The agent produces requirements, a design, and a sequenced task list as markdown files, then implements them with parallel agents on your machine or in the cloud. It checks requirements for gaps and uses property-based tests to catch edge cases that unit tests miss. A headless CLI runs the same agent in CI pipelines. It supports MCP servers, Agent Client Protocol, AGENTS.md, and Open VSX extensions. The free tier includes 50 credits per month.