Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Zed by Zed Industries

High-performance open-source code editor written in Rust, with multiplayer editing, an agent panel, edit predictions and support for external agents through the Agent Client Protocol. Version 1.0 shipped in April 2026.

AI IDEs and editor agents AI-capable code editor

Use it in: IDE Works with: MCP Local models Own API key Multi-agent

WebsiteDocsGitHub

Checked Nov 7, 2026. Tap a verdict to see its source.How we checkedReport an error

What Zed does

Zed is an AI-capable code editor from Zed Industries. You use it through desktop IDE on macOS, Linux and Windows. Its documentation covers MCP servers, subagents or parallel agents, your own API key and local models. It can run models from Anthropic, OpenAI, Google, xAI, Mistral and DeepSeek and others. Paid plans start at $10 a month; there is a free tier.

Recent developments

  • 2026-04: Zed 1.0 released.
  • 2026-08-12: Introduced Delta, a multiplayer environment for coding with agents (public beta 2026-09-16).

What people use it for

Ask the agent to change your code

Describe a bug or a small feature in the side panel; the agent searches the project, edits files and can run commands such as your tests.

Check each change before keeping it

After the agent works, open the list of edited files and keep or undo each changed piece, or all of them at once.

Run Claude or Codex inside the editor

If you already use the Claude, Codex, OpenCode or Gemini agents, install them from Zed's built-in list and chat with them in the same panel.

Keep code on your own computer

Point the agent at a model running on your machine through Ollama or LM Studio, so prompts do not go to an online model company.

Work on two tasks in parallel

Start several agent chats at once, each on its own project or its own copy of the code, so they do not overwrite each other.

Use it as a plain editor

Teams that may not use AI at work can turn every AI feature off with one setting and keep the editor.

Popularity
#3 in IDEs
Gid Score 64 / 100 · #12 of 251 ranked AI agents
Trend
Gaining stars fast
about +89 GitHub stars a day
Community
95.3K GitHub stars
public signals

Usage data: latest readings Nov 18 to Nov 19, 2026, last checked Nov 19, 06:35 UTC. Date of each number

Zed popularity and usage data

The GitHub repository has 95.3K stars, 3,652 of them added in the last 30 days. The latest stable release is 1.29.2, published Nov 18, 2026; there were 7 stable releases in the past 30 days. It was mentioned in 108 Hacker News posts and comments over the last 30 days.

GitHub starsrunning total 95.3K
Hacker News mentionsposts and comments, rolling 7-day total 15 this week
Wikipedia page viewsEnglish Wikipedia, 7-day average 140/day
Website rankTranco list; a lower rank means more traffic #17,257

Download the raw daily series: zed.csv

Gid Score breakdown

Adoption68
Community82
Attention45
Momentum52

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
Homebrew installsNov 19, 2026Nov 19, 06:26 UTC
Website rank (Tranco)Nov 18, 2026Nov 19, 06:35 UTC
Wikipedia viewsNov 18, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Pricing

Personal $0 (the editor, free; unlimited use with your own API keys or external agents such as Claude Agent and Codex CLI); Pro $10/mo (Zed-hosted models, unlimited edit predictions, $5 of tokens included, usage-based billing beyond; free trial); Business $30/seat/mo (org-wide AI policies and unified billing on top of Pro; no AI credits bundled; SSO, SAML and SCIM are planned but not yet available, Zed says).

Source: official pricing page, checked Nov 7, 2026. Prices change often; confirm before you buy.

Zed pricing history since 2024 · Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (GPL-3.0-or-later)
  • Works with local models?Yes
  • Bring your own API key?Yes
  • Runs onmacOS, Linux, Windows
  • Where you use itDesktop IDE
  • Supports MCP?Yes
  • Model providersanthropic, openai, google, xai, mistral, deepseek, amazon, openrouter, any OpenAI-compatible, local, vendor's own
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeGitHub Copilot · all alternatives

What Zed users report right now

All 5 reports, questions and fixes →

Open Users report that the Claude Agent in Zed's agent panel fails to launch with an ERR_MODULE_NOT_FOUND error because its locally installed adapter files end up incomplete; some say reinstalling it from the ACP registry did not help.

Reported on GitHub · 16 👍

Open Users report that when Claude or Codex asks to run a command in the agent panel, the approval card can show a blank field or just 'Bash' instead of the command, so they cannot review what they approve. A Zed team member reproduced the 'Bash' case and linked it to an issue in the Claude ACP adapter.

Reported on GitHub · 15 👍

Open Users report that with their own OpenRouter key, Zed sometimes blocks requests with 'Free Usage Exceeded — Upgrade to Zed Pro' while OpenRouter still bills them; some saw it when OpenRouter itself returned a payment error. A Zed team member said a linked change should fix it, but that PR is still open.

Reported on GitHub · 7 👍

Fixed in 1.24.4 Users reported that the OpenCode provider showed 'Failed to load models: missing field npm' and listed no Zen or Go models, even with a valid API key.

Reported on GitHub · 13 👍

Fixed in 1.26.2 Users reported that discarding a file's unstaged changes in the Git panel also threw away the staged changes in the same file.

Reported on GitHub · 6 👍

The most discussed problems in its GitHub repository, checked Nov 12, 2026. Written by AgentGid in its own words; statuses and fix versions come from the project's own pages. Reports are users' accounts, not AgentGid tests.

What changed: recent Zed releases

22 stable releases in the last 90 days · Monthly summary · Full changelog

1.29.2
  • Added an official Snap package for Linux
1.29.1
  • Added an agent.auto_generate_thread_titles setting (default true) that can be set to false to disable automatic title generation for Zed Agent threads. (#63998; thanks FrederickGeek8)
  • Added support for Claude Fable 5.2 for Anthropic BYOK users, plus Claude Mythos 5.2 if your organization has access.
  • Improved the copy button on agent responses to briefly show a checkmark confirming the copy. (#64664; thanks itsfuad)
  • Improved the ordering of ACP agent config options in the message editor so the first option the agent provides appears next to the send button.
  • Added a branch mode to the Git Panel that lists all files changed since a base branch, such as origin/main.
  • Added a git.date_format setting ("locale", "iso", or a strftime format such as "%Y-%m-%d %H:%M") for absolute Git dates, and date_style settings ("relative" or "absolute") to choose how dates are…
Earlier releases
1.28.1
  • Added an edit_predictions.button setting to toggle the edit prediction button in the status bar. (#66450; thanks z0al)
  • Improved compatibility with the latest Agent Client Protocol, including handling of missing sessions, plan updates, diff formats, and cancellation of permission requests.
  • Improved the Agent's read_file tool output by truncating lines longer than 2,000 characters to prevent context window overflow. (#65395; thanks Antphar)
  • Improved subagent cards so that full screen opens a finished subagent run at its start.
  • Added optional automatic fetching of the current branch's upstream remote and the default branch's remote. Enable it with git.auto_fetch.enabled.
  • Added a resizable "Refs" column to the Git Graph that can be toggled on or off from the column header's context menu. (#66260; thanks RemcoSmitsDev)
1.27.0
  • Improved Agent Panel memory usage by loading tool-call diffs and parsing thread message Markdown only when first viewed, instead of when loading a thread. (#65444, #65470; thanks Vanuan)
  • Improved AI commit message generation by using the three most recent repository commit messages as style examples. (#61528; thanks matheuslrd)
  • Improved CPU usage and disk reads while the agent was working, especially with a long thread history.
  • Added missing tooltips to the close, commit message, and "View on" buttons in the Git Graph's commit details panel. (#66016; thanks skmanoj322)
  • Improved Git Graph rendering performance. (#66180; thanks RemcoSmitsDev)
  • Improved the Git Panel's error message when a push was rejected because the local branch was behind the remote, explaining that remote changes must be fetched and integrated before pushing again.
1.26.2
  • Improved ACP configuration defaults to apply only to new conversations, preserving session settings when reopening existing conversations.
  • Improved fuzzy searching in agent model and configuration option pickers for Zed Agent and third-party ACP agents, while keeping search preparation off the UI thread. (#64147; thanks JacobNWolf)
  • Improved OpenCode compatibility when replaying DeepSeek reasoning and disabling thinking for Google models.
  • Improved thinking controls to explain when thinking cannot be disabled at the selected effort level.
  • Added DWARF debugging to the JavaScript debugger to support debugging WebAssembly sources. (#65371; thanks SGumbles)
  • Improved debugger hovers with an expandable, keyboard-accessible variable tree. (#53198; thanks Tortes)
1.25.3
  • Updated dependencies to address recent software ecosystem vulnerabilities.

Compare Zed with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
5
GitHub CopilotPromoGitHub (Microsoft)
75 — — — — — Free + $10/mo
6
CursorAnysphere (owned by SpaceX)
73 — — — 33.3K+4/day — Free + $8/mo
25 55 — — — — — Free + $30/mo
26
WarpWarp
55 — — — 66.1K+15/day 0.2026.06.03.…5mo ago Free + $20/mo
42
KiroPromoAmazon Web Services
50 — — — 4,484+4/day — Free + $20/mo
47
Amazon Q DeveloperAmazon Web Services
49 — — — 62 2.10.08d ago Free + $19/mo

Head to head: Zed vs GitHub Copilot · Zed vs Cursor · Zed vs Google Antigravity · Zed vs Warp · Zed vs Junie

Tell Zed

“Look through this project, tell me how the tests are run, then fix the failing test and show me every change before you run anything else.”

  1. On a Mac, install the app with Homebrew (or download it from zed.dev/download).

    brew install --cask zed

    From zed.dev/docs/installation

  2. On Linux use the install script; on Windows use winget.

    curl -f https://zed.dev/install.sh | sh
    winget install -e --id ZedIndustries.Zed
    
  3. Open the Agent Panel (the sparkle icon in the status bar), choose a model or an outside agent, then type your request.

    From zed.dev/docs/ai/agent-panel

Mistakes to avoid

Setting tool_permissions default to "allow" and trusting Zed to stop anything dangerous
Keep the terminal on "confirm", allow only known commands (tests, builds) and add always_deny rules for .env files, secrets and keys.

Zed's only hard-coded blocks are recursive deletes of the root, home, current or parent folder.

Expecting the Anthropic or OpenAI key saved for the Zed Agent to also work for Claude Agent or Codex
Open a Claude Agent or Codex thread and sign in there with its own login (/login for Claude Agent).

Outside agents keep their own sign-in and billing, separate from Zed's model keys.

Expecting Zed's tool permissions and profiles to guard a Claude Code or Codex session in a Terminal Thread
Set permissions inside that tool's own settings; Zed's rules cover only the Zed Agent.

In a Terminal Thread the command-line tool owns its own tools, keys and instructions.

Rating answers with thumbs up/down while working on private client code
Leave answers unrated if the thread must not be stored by Zed, or have a Business admin turn sharing off.

A rating sends the whole thread, including your messages and the AI's answers, to Zed.

Turning on trust_all_worktrees so downloaded projects open without the trust prompt
Keep Restricted Mode and trust each project only after reading its .zed/settings.json and the servers it starts.

A project's settings can download and start language servers and MCP servers on your machine.

Get started with Zed

Homebrewbrew install --cask zed

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Zed FAQ

How much does Zed cost?

Personal $0 (the editor, free; unlimited use with your own API keys or external agents such as Claude Agent and Codex CLI); Pro $10/mo (Zed-hosted models, unlimited edit predictions, $5 of tokens included, usage-based billing beyond; free trial); Business $30/seat/mo (org-wide AI policies and unified billing on top of Pro; no AI credits bundled; SSO, SAML and SCIM are planned but not yet available, Zed says).

Is Zed open source?

Yes. Zed is open source, released under the GPL-3.0-or-later license.

How popular is Zed?

The GitHub repository has 95.3K stars, 3,652 of them added in the last 30 days. The latest stable release is 1.29.2, published Nov 18, 2026; there were 7 stable releases in the past 30 days. It was mentioned in 108 Hacker News posts and comments over the last 30 days.

What is the latest version of Zed?

The latest stable release we track is 1.29.2, published on Nov 18, 2026.

What are the alternatives to Zed?

The closest alternatives in the same category by Gid Score are GitHub Copilot, Cursor, Google Antigravity, Warp.

More about Zed

What's new

What's new in Zed: September 2026

Full monthly summary

September brought expanded AI model support across multiple providers, improved agent management capabilities, and fixes for terminal input, language server issues, and editor behavior.

  • Added SuperGrok sign-in to use Grok models in the Agent Panel, plus support for Grok 4.5, 4.6, and 4.7.
  • Extended BYOK (bring-your-own-key) support to Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and GPT-6 Astra.
  • Added automatic language detection for untitled buffers and new agent spawn parameters for model selection.
  • Fixed critical issues with inline assistant reasoning, terminal input on Windows, and tab switching behavior.

7 releases this month · summarised from the official release notes · all months

Articles

AgentGid articles about Zed

All guides

Ratings

Ratings from people who use Zed

No ratings yet. Used Zed? Rate it and say what it is good and bad at.

News
  1. Release GitHub Releases

    Zed 1.29.2 released

    Added an official Snap package for Linux (+1 more release that day)

  2. Release GitHub Releases

    Zed 1.28.1 released

    Added an edit_predictions.button setting to toggle the edit prediction button in the status bar. (#66450; thanks z0al); Improved compatibility with the latest Agent Client Protocol, including handling of missing sessions, plan updates, diff formats, and…

Price history

Zed prices over time

Full pricing history →

Zed plan pricesfrom archived copies of the official pricing page
Cheapest paid planMost expensive self-serve plan
Token prices of Anthropic modelsnewest Anthropic model in each family, output price per 1M tokens
Anthropic OpusAnthropic SonnetAnthropic Haiku
Sources
For the makers of Zed badges, corrections

Add a live badge to your README or site:

AgentGid: #3 in IDEs Gid Score: 64/100

[![AgentGid: #3 in IDEs](https://agentgid.com/badges/zed-rank.svg)](https://agentgid.com/agents/zed/)
[![Gid Score: 64/100](https://agentgid.com/badges/zed-score.svg)](https://agentgid.com/agents/zed/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

GitHub: zed-industries/zed. Homebrew: zed. Wikipedia: Zed (text editor). Site rank: zed.dev on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: zed.dev, github.com, en.wikipedia.org, formulae.brew.sh.