Zed
Also known as: Zed, Zed Editor, zed.dev, Zed Industries
Open source, GPU accelerated code editor written in Rust, with a native AI agent panel, parallel agents, real time collaboration, and support for fifteen model providers.
Zed is a code editor built from scratch in Rust by Zed Industries, the team behind the Atom editor, and engineered above all for speed. It uses the graphics processor for rendering and multiple cores for indexing and language servers, so startup, scrolling, search, and keystrokes feel instant in a way Electron based editors like VS Code cannot match. It runs natively on macOS, Linux, and Windows, is open source under the Apache license, and treats real time collaboration as a first class feature, letting teammates share a project with live cursors, chat, voice, and screen sharing without plugins. It is not a VS Code fork, so its extension ecosystem is smaller but its editing engine is its own.
Since 2025 Zed has invested heavily in agentic AI. Its Agent Panel runs a native agent that discovers context, edits files, and runs tools across a multi step task, and parallel agents can run in several threads across different projects at once. An open weight edit prediction model called Zeta anticipates your next edit at keystroke granularity and can run locally. Zed also created the open Agent Client Protocol, so external agents like Claude Code, Codex, and OpenCode plug directly into the editor, and Terminal Threads run any command line agent as a persistent sidebar. Model Context Protocol servers extend an agent's tools and knowledge.
Zed does not lock users into one model. It connects to fifteen providers including Anthropic, OpenAI, Google, Amazon Bedrock, and Mistral, plus local models through Ollama and LM Studio, offering Zed hosted models with no API keys or your own keys, in which case data goes straight to your provider. Oversight is built in: you follow the agent live as it works, review its changes in an editable unified diff and accept or reject each one before committing, and use a checkpoint system to revert to the state before any edit batch. Context is added by mentioning files, symbols, diagnostics, and past threads.
For teams, a Business tier adds an admin layer with org wide model policies, data sharing controls, role based access, and unified spend visibility, though single sign on, SCIM, and a SOC 2 certification are on the roadmap rather than shipped. Being open source and supporting local and open weight models, Zed keeps code under the team's control, with remote development letting the codebase live on a server while the machine runs only the interface. Pricing is simple and low: a free Personal tier with a monthly edit prediction allowance and unlimited use of your own keys, Pro at ten dollars a month for unlimited prediction and hosted credits, and Business at thirty dollars per seat. Zed is the speed and craft choice, with native agent depth still maturing against dedicated rivals.
Vendor details
Canonical URL
https://zed.dev
Category
Coding agent
Subcategory
Open source native AI code editor with agent panel and ACP (Rust)
Funding status
Zed is built by Zed Industries, Inc., an independent company founded by the creators of the Atom editor, which Microsoft acquired and later sunset before releasing VS Code. The editor is open source under the Apache 2.0 license. Specific venture funding is not detailed in available sources. Zed accepts optional sponsorship through GitHub Sponsors, which does not grant paid features. The product reached stable releases across macOS, Linux, and Windows by 2026 and reports a growing ecosystem of extensions and agent integrations.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Runs a native agent with built in tools and connects external agents such as Claude Code, Codex, Gemini CLI, and OpenCode through the open Agent Client Protocol, plus Terminal Threads for any command line agent. Model Context Protocol servers extend agent tools and knowledge, and the editor has first class Git support for staging, committing, pushing, diffs, and more, native debugging through the Debug Adapter Protocol, language server support, and a growing ecosystem of hundreds of extensions. It connects to fifteen model providers, supports remote development, and adds context by mentioning files, symbols, diagnostics, branch diffs, threads, and fetched URLs.
In practice
You want a coding agent inside a fast native editor. Zed's Agent Panel edits files while you follow along live and review every change, and you can plug in Claude Code through its open protocol.
You care about editor speed and privacy. Zed is open source, runs local models through Ollama, and lets you bring your own keys so code and prompts go to your provider rather than Zed.
Your team pairs and reviews together. Zed's native multiplayer gives shared buffers, live cursors, voice, and screen sharing, and its Business tier adds org wide model policies, role based access, and unified spend visibility.
Sources & related URLs
Related / legacy domains
Capability coverage
9.5 / 14 capabilities · 68%
| Integrations & Tool CallingConnects a native agent and external agents through the open Agent Client Protocol, extends tools and knowledge with Model Context Protocol servers, runs command line agents as Terminal Threads, and has first class Git operations, native debugging, language servers, and hundreds of extensions, broad named integrations with real tool use and action. | Full |
|---|---|
| Workflow OrchestrationRuns a native agent that, from a task description, discovers context, edits files, and runs tools across multiple steps until the work is done, and supports parallel agents running in several threads across different projects at once, genuine autonomous multi step orchestration. | Full |
| Knowledge Grounding & RAGLets the agent search the codebase for relevant context and lets developers add context by mentioning files, directories, symbols, diagnostics, branch diffs, and previous threads, with fast multi core indexing, real context grounding, though not a deep codebase knowledge graph presented as the headline. | Partial |
| Human Oversight & GuardrailsLets a developer follow the agent live as it reads and edits files, review its work in an editable unified diff and accept or reject each change hunk before committing, and revert with checkpoints, strong review and approval oversight rather than a runtime guardrail enforcement engine. | Partial |
| Security, Identity & GovernanceAdds an organization admin layer on its Business tier with org wide model policies, data sharing controls, role based access, and unified spend visibility, and keeps credentials in secure storage, real governance, though single sign on, SAML, SCIM, and a SOC 2 certification are on the roadmap and not yet shipped. | Partial |
| Observability & AuditabilityLets developers follow the agent's navigation live, shows token usage, keeps thread history that can be restored, and gives teams unified spend visibility, real visibility into agent activity and cost, short of a comprehensive audit log, tracing, and analytics suite. | Partial |
| Memory & State PersistenceProvides a checkpoint system that reverts to the state before any edit batch and restores threads from history, an explicit persistent state and checkpoint capability, though not a broader long term agent memory product that carries learnings across sessions. | Partial |
| Deployment & Data ResidencyIs open source under the Apache license and runs entirely on the developer's machine, supports local models through Ollama and LM Studio and an open weight edit prediction model that can self host, keeps data with the provider under bring your own key, and offers remote development, a genuine self host and data residency capability. | Full |
| Prebuilt Agents, Templates & PacksShips agent skills, profiles, and instructions for shaping the native agent and lets developers plug in a roster of external agents such as Claude Code, Codex, and OpenCode through its open protocol, real agent scaffolding and a pluggable agent roster, though not a browsable marketplace of prebuilt agents and packs. | Partial |
| Triggers & Channel CoverageRuns natively on macOS, Linux, and Windows and reaches developers through the editor, Terminal Threads, remote development, and real time collaboration sessions, real multi platform channel coverage that is developer invoked during coding rather than driven by broad external event triggers. | Partial |
| Model Flexibility & RoutingConnects to fifteen model providers including Anthropic, OpenAI, Google, Amazon Bedrock, Mistral, OpenRouter, and Vercel, plus local models through Ollama and LM Studio, offering Zed hosted models with no API keys or bring your own key, genuine multi provider model flexibility and routing. | Full |
| APIs, SDKs & MCP ExtensibilityIs fully open source and offers a first class extensibility surface, an extension ecosystem with a defined extension interface, Model Context Protocol server support, and its own open Agent Client Protocol that any editor or agent can implement, a comprehensive application programming interface and extension surface. | Full |
| Testing, Debugging & OptimizationProvides native multi language debugging through the Debug Adapter Protocol and surfaces diagnostics that the agent can act on, plus agent tool use to run tests, a real debugging capability, though not a dedicated automated testing, code quality, or optimization engine. | Partial |
| Browser & Computer UseRuns command line agents and commands through Terminal Threads, executes and debugs programs natively, and lets the agent run tools in the workspace, real code execution and computer use within the editor, though not general autonomous browser automation. | Partial |
Pricing
Personal is free forever with 2,000 accepted edit predictions a month and unlimited use of your own keys. Pro is 10 dollars a month for unlimited prediction plus 5 dollars of hosted model credit. Business is 30 dollars per seat. Hosted usage beyond credit is billed at provider list price plus 10 percent.
A free editor with a monthly edit prediction allowance, then a low flat subscription. Paid tiers add unlimited edit prediction and a small hosted model credit, after which hosted usage is billed by tokens at the provider's list price plus ten percent. Bringing your own key or running local models avoids that usage cost entirely.
Included quota
Personal, free: two thousand accepted edit predictions a month, unlimited use of your own keys and external agents, local models, and full real time collaboration. Pro at ten dollars: unlimited edit predictions, five dollars of monthly hosted model credit, then hosted usage at provider list price plus ten percent, and priority access to frontier models. Business at thirty dollars per seat: an admin layer with org wide model policies, data governance, role based access, and unified spend, with members able to keep their own Pro plans. Students get Pro features free.
What is public
Public and exact: the three tier prices, the free tier contents, the ten percent usage markup, and the roadmap status of enterprise identity features. Set by providers: the underlying per token model rates.
Billing mechanics
A free Personal tier, Pro at ten dollars a month, and Business at thirty dollars per seat, with hosted model usage metered by tokens at provider list price plus ten percent above a small credit, and bring your own key or local models as a zero markup path.
Cost watchouts
Hosted model usage beyond the small included credit is billed by tokens at the provider's list price plus ten percent, so heavy use of frontier models like Opus adds up. Bringing your own key or using local models avoids the markup but shifts spend to your provider or hardware. Business seats do not bundle a fixed model credit.
Variable cost rationale
Hosted model usage is token metered at provider list price plus ten percent above a small monthly credit, so cost scales with how much and which models are used, which is real exposure. However, a free tier, unlimited edit prediction on Pro, and a bring your own key or local model path let a developer cap or avoid usage billing entirely, so exposure is moderate and controllable rather than high.
Additional watchouts
Frontier model usage on hosted billing adds up quickly beyond the small credit, and enterprise identity and compliance features, single sign on, SAML, SCIM, and SOC 2, are not yet shipped, which may block regulated buyers despite the strong data control from open source and bring your own key.
Overage / add-ons
Hosted model usage above the included monthly credit is billed by tokens at the provider's list price plus ten percent, charged either at month end or per ten dollars of usage, whichever comes first. Bringing your own key routes spend directly to the provider with no markup.
Sales call required
No — self-serve available
Free / trial
A free Personal tier is free forever and includes two thousand accepted edit predictions a month, unlimited use with your own keys or external agents, local models, and full real time collaboration. Students get Pro features free, and a two week Pro trial includes twenty dollars of credits.
Lowest paid plan
Pro at ten dollars a month, above a free Personal tier. Pro dropped from twenty to ten dollars in May 2026.
Commercial notes
At ten dollars, Pro is one of the cheapest paid AI editor plans, roughly half of Cursor, and the open source editor plus bring your own key path means many developers pay nothing. Transparent token billing at provider list price plus ten percent is a deliberate contrast to bundled credit systems, appealing to developers who want predictable, provider aligned costs.
Key ambiguities
Because hosted model usage is token metered above a small credit, the real monthly cost depends on which models are used and how heavily, though bringing your own key or local models makes cost predictable. Business seats meter hosted usage separately rather than bundling a fixed allowance.
Cancellation / refund
Self serve monthly plans can be changed or cancelled by the user. There is a two week Pro trial with twenty dollars of credits. The editor itself is free and open source, so there is no lock in at that level.
Missing data
Annual pricing, if any, and exact hosted model rates per provider are set by the underlying providers plus the ten percent markup rather than published as fixed Zed prices.
Related vendors
- Cognition — Maker of Devin, an autonomous AI software engineer
- Aider — Open-source, model-agnostic terminal coding agent that works…
- Anthropic Claude Code — Anthropic's terminal and IDE-native coding agent with sub-agent…
- Augment Code — AI coding assistant evolving into an AI-native engineering platform
- Blackbox AI — AI coding assistant for code generation and developer workflows
- Blink — Agentic AI app builder that turns a natural language prompt into a…