Skip to content

Rank #2 of 6 in Terminals

iTerm2 logo

iTerm2

Open Source Built-in AI assistant

George Nachman / iTerm2 contributors

18k1.2k/yr +37

Showcase

iTerm2 homepage screenshot
homepage · captured Sep 2026 · view live ↗
iTerm2 docs screenshot
docs · captured Sep 2026 · view live ↗

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

18.7/100

Ai assistance — stories about ai assistance in this arenaAi assistanceevidence →

Stories about ai assistance in this arena

26.7/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

37.5/100

Config theming — stories about config theming in this arenaConfig themingevidence →

Stories about config theming in this arena

0.0/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

14.4/100

Panes multiplexing — stories about panes multiplexing in this arenaPanes multiplexingevidence →

Stories about panes multiplexing in this arena

86.7/100

Performance rendering — stories about performance rendering in this arenaPerformance renderingevidence →

Stories about performance rendering in this arena

0.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

12.0/100

Protocols media — stories about protocols media in this arenaProtocols mediaevidence →

Stories about protocols media in this arena

40.0/100

Remote ssh — stories about remote ssh in this arenaRemote sshevidence →

Stories about remote ssh in this arena

85.0/100

Scriptability control — stories about scriptability control in this arenaScriptability controlevidence →

Stories about scriptability control in this arena

80.0/100

Shell integration — stories about shell integration in this arenaShell integrationevidence →

Stories about shell integration in this arena

85.0/100

Workflow ergonomics — stories about workflow ergonomics in this arenaWorkflow ergonomicsevidence →

Stories about workflow ergonomics in this arena

72.8/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 54/54 stories · click a row’s chevron for the rationale and evidence

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial6/10X

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3noneuntestednone yet

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10X

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10X

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10X

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial4/10T

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1n/auntestednone yet

Split windows into panes and organize work across tabs without an external multiplexer C

Multiplexing

developerPanes multiplexing — stories about panes multiplexing in this arenaPanes multiplexing3full9/10C

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3full8/10C

Let a coding agent programmatically drive the terminal itself — create panes, run commands, read output — through a documented control protocol or API C

Agent control

ai-native userScriptability control — stories about scriptability control in this arenaScriptability control3full8/10X

Script and control the terminal from the command line — open windows, send text, query state — via a documented CLI or IPC interface C

Remote control

developerScriptability control — stories about scriptability control in this arenaScriptability control3full8/10X

Delegate terminal tasks to a built-in AI agent that plans and executes commands with my approval C

Ai agent

ai-native userAi assistance — stories about ai assistance in this arenaAi assistance3partial5/10X

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3disputed4/10D

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3none0/10

Keep the terminal's full configuration as plain-text files in my dotfiles and sync it across machines C

Dotfiles

power-userConfig theming — stories about config theming in this arenaConfig theming3noneuntestednone yet

Rely on GPU-accelerated rendering that stays fast and responsive under heavy output C

Rendering

developerPerformance rendering — stories about performance rendering in this arenaPerformance rendering3noneuntestednone yet

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3noneuntestednone yet

Jump between prompts and command marks in my scrollback thanks to shell integration C

Marks

developerShell integration — stories about shell integration in this arenaShell integration2full9/10C

Open URLs and file paths from output by clicking them or selecting them from the keyboard C

Hyperlinks

developerWorkflow ergonomics — stories about workflow ergonomics in this arenaWorkflow ergonomics2full9/10X

Use tmux inside the terminal, or a documented native tmux integration/control mode C

Tmux

developerRemote ssh — stories about remote ssh in this arenaRemote ssh2full9/10C

Define startup sessions and window layouts in config or scripts so a project workspace opens in one command C

Layouts

power-userScriptability control — stories about scriptability control in this arenaScriptability control2full8/10X

Display inline images and rich graphics via a documented terminal graphics protocol C

Graphics

developerProtocols media — stories about protocols media in this arenaProtocols media2full8/10X

Extend the terminal with scripts or plugins in a real language (Lua, Python, kittens) beyond built-in options C

Extensibility

developerScriptability control — stories about scriptability control in this arenaScriptability control2full8/10X

I get command-aware features from shell integration, like exit status, duration, and notifications when long commands finish C

Command tracking

developerShell integration — stories about shell integration in this arenaShell integration2full8/10C

Restore my windows, tabs, and working directories after a restart or crash C

Sessions

developerPanes multiplexing — stories about panes multiplexing in this arenaPanes multiplexing2full8/10C

Search my scrollback quickly and jump between matches C

Scrollback

developerWorkflow ergonomics — stories about workflow ergonomics in this arenaWorkflow ergonomics2full8/10C

SSH to remote hosts with the terminal's own integration carrying my terminfo, shell integration, and config along C

Ssh

developerRemote ssh — stories about remote ssh in this arenaRemote ssh2full8/10X

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial6/10T

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial6/10C

Get AI explanations and suggested fixes when a command fails C

Ai commands

ai-native userAi assistance — stories about ai assistance in this arenaAi assistance2partial5/10C

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2disputed5/10D

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial5/10C

Type natural language and get the right shell command generated in place C

Ai commands

ai-native userAi assistance — stories about ai assistance in this arenaAi assistance2partial5/10X

Use or fully disable AI features with clear control over what session data leaves my machine, without a forced login C

Ai privacy

ai-native userAi assistance — stories about ai assistance in this arenaAi assistance2disputed5/10D

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2disputed3/10D

Run the same terminal with the same config on macOS, Linux, and Windows C

Platforms

developerProtocols media — stories about protocols media in this arenaProtocols media2none0/10

Apply color schemes and themes, including automatic light/dark mode switching C

Theming

power-userConfig theming — stories about config theming in this arenaConfig theming2noneuntestednone yet

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2n/auntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

See published benchmarks or measured latency/throughput numbers backing the terminal's performance claims C

Benchmarks

power-userPerformance rendering — stories about performance rendering in this arenaPerformance rendering2noneuntestednone yet

Use programming fonts with ligatures, fallback fonts, and fine-grained font tuning C

Fonts

developerConfig theming — stories about config theming in this arenaConfig theming2noneuntestednone yet

Summon the terminal instantly with a global hotkey or quake-style dropdown window C

Quick access

power-userPanes multiplexing — stories about panes multiplexing in this arenaPanes multiplexing1full9/10C

Discover and run terminal actions from a searchable command palette C

Discoverability

power-userWorkflow ergonomics — stories about workflow ergonomics in this arenaWorkflow ergonomics1partial4/10C

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1noneuntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 32 stories with headroom

What would move iTerm2’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    nonemoves agent-readyimpact 45

    iTerm2 has an AI chat plugin and Python scripting API, but no evidence anywhere in the pack of MCP server integration or ability to plug in MCP tools.

  2. Agenticness — how well agents can access and operate the productConnect an agent via an official MCP server

    nonemoves agent-readyimpact 45

    No evidence of an official MCP server for iTerm2; it offers an AI chat plugin (OpenAI-based) and Python/AppleScript scripting APIs, but nothing about MCP protocol support.

  3. Config theming — stories about config theming in this arenaKeep the terminal's full configuration as plain-text files in my dotfiles and sync it across machines

    nonemoves PA Scoreimpact 30

    The evidence pack contains no mention of iTerm2's preferences file format, exporting/importing settings as plain-text/plist files, or any dotfiles-style sync workflow across machines.

  4. Performance rendering — stories about performance rendering in this arenaRely on GPU-accelerated rendering that stays fast and responsive under heavy output

    nonemoves PA Scoreimpact 30

    No evidence in the pack mentions GPU acceleration, rendering architecture, or performance under heavy output/scrollback; the docs and community items cover features like panes, triggers, search, and scripting but nothing about rendering performance or GPU usage.

  5. Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave

    nonemoves PA Scoreimpact 30

    Missing: documented export of preferences/profiles/history in open formats, data portability guarantees, migration/export tooling.

  6. Openness — open source, data portability, and self-hosting storiesSelf-host the core product

    nonemoves PA Scoreimpact 30

    The axis applies to terminal emulators as a kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".

  7. Agenticness — how well agents can access and operate the productPoint an agent at llms.txt or agent-oriented docs

    nonemoves agent-readyimpact 30

    Probes explicitly show no llms.txt or machine-readable/agent-oriented docs endpoint exists (404s), and no other evidence indicates agent-oriented documentation formats are offered.

  8. Agenticness — how well agents can access and operate the productRun the product headlessly / in CI for automation

    nonemoves agent-readyimpact 30

    The axis applies to terminal emulators as a kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".

Showing the top 8 of 32 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map10 surfaces · 33 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

GitHub README25 stories

Hacker News21 stories

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

5 of 15 testable claims verified · 2 contradictedintegrity 7/100

29 distinct capability claims found in iTerm2’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

5

Verified

8

Unverified

2

Contradicted

16

Undersold

Verified (5)
Unverified (11)
Contradicted (2)
Undersold (16)
Claims outside our story set (11)

Real capability claims found in iTerm2’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • Autocomplete popup (Cmd-;) suggests previously typed words in the window

    source ↗
  • Keyboard-driven text selection and modification (Copy Mode)

    source ↗
  • Paste history lets you revisit and optionally persist recently copied/pasted text

    source ↗
  • Instant replay lets you scroll back in time to recover erased terminal text

    source ↗
  • Browser profiles integrate web browsing into the window/tab/pane hierarchy with terminal features like AI chat

    source ↗
  • Open Quickly (Cmd-Shift-O) searches across all sessions by title, command, hostname, directory, or badge

    source ↗
  • Configurable per-session status bar showing git branch, CPU/memory, directory, hostname, or custom components

    source ↗
  • Smart Cursor Color and Minimum Contrast features improve cursor/text visibility automatically

    source ↗
  • Taggable, searchable database of connection profiles

    source ↗
  • Global Search lets you search text across all open tabs at once

    source ↗
  • Mouse reporting feature lets you position cursor and interact with programs like Vim/Emacs via mouse

    source ↗
Suggest a story for these →

Business model

open-source

Free, GPL-2.0 open source macOS terminal maintained by George Nachman; no paid tiers, funded by user donations and GitHub Sponsors.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Scoretracked since Sep 16 '26 — no movement recorded yet
Agent-readytracked since Sep 16 '26 — no movement recorded yet

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

Data