Zed
FreemiumZed 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.
Key features
- Open-source editor with GPU-accelerated rendering
- Agent panel for project-wide edits and commands
- Edit predictions while typing
- Bring your own API keys or use hosted models
- Real-time multiplayer editing
- Runs external agents through the Agent Client Protocol
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.
AutoGPT
AutoGPT began as an open-source autonomous agent project and now ships a hosted platform built around named AI specialists. You pick an expert for content, sales, research or administration, brief it in plain language, and connect the accounts it may use. A coordinating assistant called Otto routes requests to the right specialist and can pull several into one job. Experts run on schedules, and each has its own spending approval threshold. A workflow builder remains available for defining steps by hand, and the whole platform can still be self-hosted with Docker.
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.
CrewAI
CrewAI provides both an open-source Python framework and a hosted studio for building multi-agent systems. In the studio you describe a process in plain language or sketch it on a canvas, and the builder assembles agents with roles, tools and an order of steps. Workflows export as a Python project, an MCP server or a UI component, and connect to GitHub for version control. The runtime records every model and tool call for tracing, and adds approval gates, PII redaction and role-based access for teams that need oversight before agents reach production systems.
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.