Back to vendors
Z

Zed

Also known as: Zed Zeta, Agent Client Protocol

Visit site
Entry pricePersonal is free forever, with unlimited use of your own keys, external agents and local models. Pro is $10 a month for unlimited edit predictions plus $5 of hosted model credit, with hosted usage beyond it at provider list price plus 10 percent. Business is $30 per seat, with hosted AI billed at standard usage rates.Full pricing detail

Open-source, GPU-accelerated Rust code editor with a native AI agent panel, parallel agents in isolated worktrees, per-tool permissions, and the open Agent Client Protocol that lets Claude Agent, Codex and OpenCode run inside the editor.

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 respond instantly. 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. It offers Zed hosted models that need 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 still on the roadmap and not 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. Personal is free, with unlimited use of your own keys, external agents and local models. Pro costs $10 a month for unlimited edit predictions and $5 of hosted model credit, and Business costs $30 per seat, with hosted AI billed at standard usage rates. Zed is built for speed and craft, and its native agent is still maturing.

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

fast native AI code editingnative and pluggable coding agents in the editorreal time collaborative and pair programmingprivate BYOK and local model coding

Target customers

performance focused and craft focused developersteams wanting native real time collaborationdevelopers who prefer open source and model choiceVim and modal editing users

Deployment options

Open-source (Apache 2.0), self-installable on macOS, Linux, WindowsLocal models via Ollama and LM StudioBYOK (data goes to your provider, not Zed)Open-weight Zeta edit-prediction model (self-hostable)Remote development (codebase on a remote server)

Integrations

Runs a native first-party agent with built-in tools and hosts external agents including Claude Agent, Codex, Copilot, Cursor, Gemini CLI and OpenCode through the open Agent Client Protocol, which Zed itself authored and publishes; Terminal Threads run any command line agent as a persistent sidebar. MCP servers extend agent tools and knowledge, and Tool Permissions govern what those tools may do. The editor has first-class Git support for staging, committing, pushing and diffs, native debugging through the Debug Adapter Protocol, language server support, roughly 800 extensions, and remote development over SSH. Three model paths are documented separately: Zed-hosted models with no API keys, local models through Ollama or LM Studio where nothing leaves the machine, and bring-your-own-key to any provider, spanning fifteen providers including Anthropic, OpenAI, Google, Amazon Bedrock, Mistral, OpenRouter and Vercel. Context is added by mentioning files, directories, 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 and not through 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.

Agentic Index coverage score

10.0 / 14 capabilities · 71%

Integrations & Tool Calling Full

A native first-party agent runs with built-in tools, while external agents including Claude Agent, Codex, Copilot, Cursor, Gemini CLI and OpenCode connect through the open Agent Client Protocol. Terminal Threads run any command line agent as a persistent sidebar, and MCP servers extend agent tools and knowledge.

The editor itself provides first-class Git operations for staging, committing, pushing and diffs, native debugging through the Debug Adapter Protocol, language server support, roughly 800 extensions, and remote development over SSH. Context is added by mentioning files, directories, symbols, diagnostics, branch diffs, previous threads and fetched URLs.

Sourcezed.dev/ai, zed.dev/docs/ai/mcp and zed.dev/extensionsread 2026-08-30

Workflow Orchestration Full

The spawn_agent tool in Zed Agent starts a subagent with its own context window for a delegated task, such as a parallel investigation while the parent continues and then reviews the findings. Parallel agent threads and Terminal Threads run at once from the Threads Sidebar across projects, with Git worktrees isolating each thread's changes.

Sourcezed.dev/docs/ai/tools and /docs/ai/parallel-agentsread 2026-09-29

Knowledge Grounding & RAG Partial

The agent searches the codebase for relevant context during a task, and developers add context by mentioning files, directories, symbols, diagnostics, branch diffs, previous threads and fetched URLs, with multi-core indexing and language servers making retrieval fast. Agent Profiles, Skills and Instructions carry standing project guidance, and thread history can be restored as context. There is no repository index product, semantic retrieval layer, dependency graph or cross-file reasoning surface, and project-wide context depends heavily on what the developer passes in.

Sourcezed.dev/docs/ai/agent-panel and zed.dev/docs/ai/overviewread 2026-08-30

Human Oversight & Guardrails Full

Tool approval is set through agent.tool_permissions. It has a global default of allow or confirm, per-tool defaults, always_allow patterns, always_confirm patterns that prompt case by case (for example sudo commands) regardless of other settings, and auto-deny rules for dangerous actions that hold even when the default is allow. Zed Agent tool calls can also run in an OS-level sandbox. After a run the developer reviews changes in an editable unified diff, accepting or rejecting each, and checkpoints revert any edit batch.

Sourcezed.dev/docs/ai/tool-permissions, /docs/ai/sandboxing and /docs/ai/agent-panelread 2026-09-29

Security, Identity & Governance Partial

Work toward SOC 2 Type 1 certification is under way, and SSO, SAML and SCIM are planned but not available. The Business admin layer is shipped, with organization roles and permissions, org-wide AI model policies, data governance controls and unified spend visibility, and local and bring-your-own-key paths keep code away from Zed.

Sourcezed.dev/docs/soc2, /docs/roles and zed.dev/pricingread 2026-09-29

Observability & Auditability Partial

Developers follow the agent live as it navigates the codebase, using the same multiplayer infrastructure that powers human collaboration, with responses streaming and indicators showing which tools the model is using. Token usage is displayed, threads can be restored from history, and unified spend visibility is available to teams on Business.

Zed publishes public agent metrics comparing usage across Zed Agent, Claude Agent and Codex CLI over rolling windows. Thread history, checkpoints and token display depend on the agent integration and vary for external agents. There is no retained per-action execution trace, audit log or replay.

Sourcezed.dev/docs/ai/agent-panel, zed.dev/agent-metrics and zed.dev/businessread 2026-08-30

Memory & State Persistence Partial

A checkpoint system reverts the workspace to the state before any edit batch, and threads can be restored from history so a session can be resumed later, though these features depend on the agent integration and vary across external agents. Agent Profiles, Skills and Instructions persist as configuration the customer writes and the agent reads on every run, and parallel Git worktrees hold isolated state per agent thread. There is no memory layer that builds up learned context, preferences or corrections across sessions.

Sourcezed.dev/docs/ai/agent-panel and zed.dev/docs/ai/overviewread 2026-08-30

Deployment & Data Residency Full

Zed is open source under Apache 2.0 and runs as a native application on macOS, Linux and Windows entirely on the developer's own machine, with the source publicly cloneable. Local models run through Ollama or LM Studio, and Zed says nothing leaves the machine.

Bring your own key sends data directly to the customer's chosen provider, not through Zed, and the Zeta edit-prediction model is open-weight, with self-hosted Next Edit models supported.

Remote development keeps the codebase on a server the customer controls while the local machine runs only the interface, and the editor works fully without AI features or any signed-in account.

Sourcezed.dev/ai, zed.dev/docs/ai/llm-providers and zed.dev/edit-predictionread 2026-08-30

Prebuilt Agents, Templates & Packs Full

The ACP Registry is the primary way to install External Agents. It opens from the command palette or Agent Settings and lists ready agents such as Claude Agent, Codex, Gemini CLI, OpenCode, Copilot, Cursor and Pi Coding Agent, and an installed agent appears in the new-thread menu. Agent Server Extensions publish further agents through the Zed Extension Registry, and Zed Agent is shaped by reusable Agent Profiles, Skills and Instructions. Each agent in the registry installs in one step.

Sourcezed.dev/docs/ai/external-agents and /docs/extensions/agent-serversread 2026-09-29

Triggers & Channel Coverage Partial

Zed runs natively on macOS, Linux and Windows with the AI features reached from the Agent Panel inside the editor, alongside a Threads sidebar, Terminal Threads running command line agents persistently, inline assistance in the buffer, remote development over SSH against a codebase held on a server, and real-time collaboration sessions where multiple humans and the agent share the same workspace. The developer starts work by typing in the message editor or invoking inline assistance. There is no event-driven trigger, scheduled run or inbound chat or ticketing channel.

Sourcezed.dev/ai and zed.dev/docs/ai/agent-panelread 2026-08-30

Model Flexibility & Routing Full

There are three model paths. Zed-hosted models, including Claude Opus and GPT 5.4, need no API keys to manage, local models run through Ollama and Zed says nothing leaves the machine, and bring your own keys works with any provider using the customer's existing accounts and budgets, with LM Studio also supported.

Fifteen providers are supported, including Anthropic, OpenAI, Google, Amazon Bedrock, Mistral, OpenRouter and Vercel, and merged community contributions continue to add providers and models including Gemini 3.7 Flash and OpenRouter effort-based reasoning. The Zeta edit-prediction model is open-weight and self-hostable, with self-hosted Sweep Next Edit models also supported.

Sourcezed.dev/ai, zed.dev/docs/ai/llm-providers and zed.dev/edit-predictionread 2026-08-30

APIs, SDKs & MCP Extensibility Full

The Agent Client Protocol, which Zed authored and publishes, is an open standard with its own site for connecting any agent to any client. Zed, the Zeta model and ACP are all open source and built in public. The editor is Apache 2.0 with a public repository, a defined extension interface and roughly 800 published extensions, MCP server support extends agent tools and knowledge, and Tool Permissions expose settings for what those tools may do. Community contributions to the AI subsystem are merged continuously and listed publicly, including provider additions and agent model updates.

Sourcezed.dev/acp, zed.dev/ai and zed.dev/extensionsread 2026-08-30

Testing, Debugging & Optimization Partial

Native multi-language debugging is built in through the Debug Adapter Protocol, language servers surface diagnostics that can be mentioned as agent context and acted on, and the agent runs tests and other commands as tools within the workspace, with results visible as it works. Zed publishes editor performance benchmarks and a public agent metrics page comparing how developers use different agents, but both measure Zed and the ecosystem and are not a harness the customer points at agent behavior. There is no test generation, evaluation or regression testing product.

Sourcezed.dev/ai and zed.dev/docs/ai/agent-panelread 2026-08-30

Browser & Computer Use Not documented

The agent works through programmatic surfaces throughout, file reads and edits in the workspace, tool calls governed by the Tool Permissions system, MCP servers, Terminal Threads running command line processes, native debugging through the Debug Adapter Protocol, language servers, and Git operations. There is no browser control, screenshot capture, visual verification or way to operate software that lacks a programmatic interface. External agents connected over ACP may carry their own browser tooling, which belongs to those agents, not to Zed.

Sourcezed.dev/ai and zed.dev/docs/ai/agent-panelread 2026-08-30

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·Human approval / guardrailsVerified

Agent checkpoints and the Restore Checkpoint button are gone from the Agent Panel in Zed 1.27.0 on the Stable channel. Taking a checkpoint before every message made the agent slow to respond, or hang, in large Git repositories. To undo an agent's changes, users now reject its edits or use Git.

Bears on: Human approval / guardrails

View source
·Agent capabilityVerified

Context compaction and session notices now work for external agents that connect to Zed over the Agent Client Protocol (ACP), starting with release 1.25.2. A third party agent running in the editor can compact a long conversation and show its session notices inside Zed.

Bears on: MCP / tool calling / API

View source
·Workflow orchestrationVerified

A parent agent in Zed 1.22.0 can now choose the model for each subagent it spawns instead of using one configured subagent model, and subagents now compact their context when it fills up.

Bears on: Workflow orchestration

View source
View all 5 Zed updates →Tracked since Jul 2026 · Verified from public vendor sources

Pricing

Personal is free forever, with unlimited use of your own keys, external agents and local models. Pro is $10 a month for unlimited edit predictions plus $5 of hosted model credit, with hosted usage beyond it at provider list price plus 10 percent. Business is $30 per seat, with hosted AI billed at standard usage rates.

A free editor that runs on the customer's own keys, external agents or local models, then a low flat subscription. Pro adds 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, and Business seats bill hosted AI at standard usage rates. Bringing your own key or running local models avoids that usage cost entirely.

Free tierTrial available

Included quota

Personal is free, with unlimited use of your own keys and external agents, local models and full real time collaboration. Pro at $10 adds unlimited edit predictions, $5 of monthly hosted model credit, hosted usage beyond it at provider list price plus ten percent, and priority access to frontier models. Business at $30 per seat adds an admin layer with org wide model policies, data governance, role based access and unified spend, bundles no fixed model credit, and lets members keep their own Pro plans. Zed's docs also describe a free Student plan for verified university students.

What is public

The three tier prices, the free tier contents, Pro's ten percent usage markup and the roadmap status of enterprise identity features are all published exactly. The underlying per token model rates are set by the providers.

Billing mechanics

A free Personal tier, Pro at $10 a month, and Business at $30 per seat. Pro meters hosted model usage by tokens at provider list price plus ten percent above a small credit, Business bills hosted AI at standard usage rates, and bring your own key or local models is a zero markup path.

Cost watchouts

Hosted model usage beyond Pro's small included credit is billed by tokens at the provider's list price plus ten percent, so heavy use of frontier models 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 metered by tokens at the provider's list price plus ten percent once Pro's small monthly credit is spent, so the bill grows with how much a developer uses hosted models and which ones, and frontier models cost most. Usage is charged at month end or for every $10 incurred, whichever comes first. Several things limit it. Edit predictions are unlimited on Pro, Personal is free, and bringing your own key or running local models takes usage off Zed's bill entirely, sending it to the provider with no markup or to the developer's own hardware. Business seats bundle no fixed model credit, so a team's hosted usage is billed on top of its seats.

Additional watchouts

Frontier model usage on hosted billing adds up quickly beyond the small credit. Single sign on, SAML, SCIM and SOC 2 are not yet shipped, which may block regulated customers despite the strong data control that open source and bring your own key give.

Overage / add-ons

On Pro, 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 $10 of usage, whichever comes first. Business bills hosted AI at standard usage rates with no bundled credit. Bringing your own key routes spend directly to the provider with no markup.

Sales call required

No, self serve available

Free / trial

Personal is free forever, with unlimited use of your own keys, external agents and local models. Pro has a 14 day free trial with $5 of hosted model usage and unlimited edit predictions, no card required.

Lowest paid plan

Pro at $10 per month, with unlimited edit predictions and $5 of hosted model tokens

Commercial notes

Pro costs $10 a month, and the open source editor and the bring your own key path mean many developers pay nothing. On Pro, hosted usage beyond the small credit is billed by tokens at provider list price plus ten percent.

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

Monthly plans can be canceled at any time. Business is month to month with no seat minimum and no free trial. 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.

Agentic Index verified 2026-10-25

Alternatives to Zed

The closest documented capability profiles to Zed among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • 10Web9.0 / 14A lighter documented profile than Zed
  • Bubble10.0 / 14Fuller documented coverage on Security, Identity & Governance
  • CodeGPT10.0 / 14Fuller documented coverage on Knowledge Grounding & RAG
  • Blackbox AI8.5 / 14A lighter documented profile than Zed
  • OpenCode10.5 / 14Fuller documented coverage on Security, Identity & Governance and Triggers & Channel Coverage
  • ThinkReview8.5 / 14A lighter documented profile than Zed

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Head to head

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.