Skip to content
ADE Index

Gemini CLI vs Codex CLI vs Pi vs Trae Agent

Up to four tools, row by row. We do not guess: a cell we have not checked says so.

This page compares the four CLI agents only. Gemini CLI has 1 other listing, Codex has 5 other listings and Trae has 1 other listing, each with its own page.

How they differ

Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

Checked for Gemini CLI, Codex CLI and Pi, not yet for Trae Agent: Price (Gemini CLI: ; Codex CLI: ; Pi: ), Model providers (Gemini CLI: ; Codex CLI: , , , , LM Studio; Pi: , , , , , SpaceXSI (Grok), , , , , , Z.ai, , , , , , , , , , , , OpenCode Console (OpenCode Zen), , Alibaba (Qwen), , , , , Meta AI (Llama), , Microsoft Foundry (Azure AI Foundry), TypeSafe AI, , , ), Systems (Gemini CLI: , , ; Codex CLI: , , , ; Pi: , , , )

Not yet checked for any of these tools: agents it runs.

Provider names use the same listing as each tool page. Dotted values open their quote.

What each can do

Select an answer to see the maker’s sentence, or what we searched.

We have not checked Trae Agent’s capabilities yet. 27 capabilities are checked for at least two of these tools. 8 get different answers, among them Approval modes, Subagents, Plan mode and Review diffs; 4 differ only in a limit. 5 others are checked for one tool only.

Differences only12
  • Yesthe maker documents it
  • With add-onAdd-onsomething the maker publishes that you install or run
  • No, per makerNothe maker says it does not
  • *its limit or add-on is named under the row
  • Emptynot yet checked
  • From the listingthe listing’s own facts; not one of the capabilities we check

Models, keys and usage

Bring your own keyFrom the listing
Local modelsNot yet checked: Gemini CLI, Trae Agent
Not yet checked for Gemini CLI
Not yet checked for Trae Agent
Custom OpenAI-compatible endpointNot yet checked: Gemini CLI, Trae Agent
Not yet checked for Gemini CLI
Not yet checked for Trae Agent
Token and cost usageNot yet checked: Trae Agent
Not yet checked for Trae Agent

MCP, hooks, skills and subagents

MCP serversNot yet checked: Trae Agent
local and remote
local and remote
local and remote
Not yet checked for Trae Agent
HooksNot yet checked: Trae Agent
Not yet checked for Trae Agent
SkillsNot yet checked: Trae Agent
Not yet checked for Trae Agent
SubagentsNot yet checked: Trae Agent
Not built in; Subagent example
Not yet checked for Trae Agent
PluginsNot yet checked: Trae Agent
Not yet checked for Trae Agent
Custom commandsNot yet checked: Trae Agent
Not yet checked for Trae Agent

Editors, scripts and CI

Editor integrationNot yet checked: Pi, Trae Agent
Gemini CLI Companion extension
Codex editor extension
Not yet checked for Pi
Not yet checked for Trae Agent
Headless modeNot yet checked: Trae Agent
Not yet checked for Trae Agent
JSON outputNot yet checked: Trae Agent
Not yet checked for Trae Agent
GitHub integrationNot yet checked: Gemini CLI, Pi, Trae Agent
Not yet checked for Gemini CLI
Codex GitHub Action
Not yet checked for Pi
Not yet checked for Trae Agent

Review, steer and undo

Plan modeNot yet checked: Trae Agent
Not built in; Plan Mode example
Not yet checked for Trae Agent
Read-only modeNot yet checked: Trae Agent
Not built in; Plan Mode example
Not yet checked for Trae Agent
Review diffsNot yet checked: Pi, Trae Agent
Gemini CLI Companion extension
Not yet checked for Pi
Not yet checked for Trae Agent
Undo file editsNot yet checked: Codex CLI, Trae Agent
Not yet checked for Codex CLI
Maker's git-checkpoint example
Not yet checked for Trae Agent

Parallel agents

Git worktreesNot yet checked: Pi, Trae Agent
Experimental; turn on first
Local execution only
Not yet checked for Pi
Not yet checked for Trae Agent

Context and memory

Project instruction filesNot yet checked: Trae Agent
Not yet checked for Trae Agent
Memory across sessionsNot yet checked: Pi, Trae Agent
Off by default; local memories
Not yet checked for Pi
Not yet checked for Trae Agent
Resume a sessionNot yet checked: Trae Agent
Not yet checked for Trae Agent
Browse past sessionsNot yet checked: Trae Agent
Not yet checked for Trae Agent

Remote and mobile control

Remote controlNot yet checked: Gemini CLI, Pi, Trae Agent
Not yet checked for Gemini CLI
To a running app server
Not yet checked for Pi
Not yet checked for Trae Agent
NotificationsNot yet checked: Trae Agent
Experimental; off by default
Maker's notify example
Not yet checked for Trae Agent

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Trae Agent
Opt-in; Seatbelt is macOS only
Linux/WSL2 needs bubblewrap
Gondolin micro-VM example
Not yet checked for Trae Agent
Approval modesNot yet checked: Trae Agent
Not yet checked for Trae Agent
Runs in a containerNot yet checked: Codex CLI, Trae Agent
Opt-in Docker or Podman sandbox
Not yet checked for Codex CLI
The repo's Docker recipe
Not yet checked for Trae Agent
Telemetry opt-outNot yet checked: Gemini CLI, Codex CLI, Trae Agent
Not yet checked for Gemini CLI
Not yet checked for Codex CLI
Not yet checked for Trae Agent

Images, web and your computer

Image inputNot yet checked: Trae Agent
Needs a compatible terminal
Not yet checked for Trae Agent
Fetch URLsNot yet checked: Codex CLI, Pi, Trae Agent
Not yet checked for Codex CLI
Not yet checked for Pi
Not yet checked for Trae Agent
Voice inputNot yet checked: Gemini CLI, Pi, Trae Agent
Not yet checked for Gemini CLI
Only in builds with voice
Not yet checked for Pi
Not yet checked for Trae Agent
Not yet checked: , , ,

5 capabilities are not yet checked for any of these tools and are not shown. Each answer is about the CLI agent in its column. Something the maker publishes separately, such as an editor plugin or a GitHub Action, shows as “With add-on”, even when it has its own listing here. How capabilities are checked

About these tools

Gemini CLI

Codex CLI

Pi

Trae Agent

How to read the Index score

At a glance

Index score out of 100

Gemini CLI44Codex CLI91Pi78Trae AgentNot enough data yet

Mindshare HN mentions, 90 days

Gemini CLI58Codex CLI4,237Pi1,310Trae Agent0

Adoption GitHub stars, not scored

Gemini CLI109kCodex CLI136kPi123kTrae Agent12.2k

Release days last 90 days

Gemini CLI12Codex CLI32Pi19Trae Agent0

Lowest monthly plan billed monthly, lower is cheaper

Gemini CLINot yet checkedCodex CLI$20/monthPiNot yet checkedTrae AgentNot yet checked

Platforms systems and surfaces

Gemini CLI3Codex CLI4Pi4Trae Agent1

Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. After activation, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built

Differences only
4 of 4
Gemini CLIgoogle-gemini · CLI agent
Codex CLIOpenAI · CLI agent
PiEarendil Works · CLI agent
Trae AgentByteDance · CLI agent
Interface
Terminal session after an MCP tool call generated three image files
Codex CLI explaining a codebase, with an updated plan checklist
pi startup listing loaded context, skills and extensions, then reading docs and running bash
What it is
Open-source terminal agent for enterprise Gemini Code Assist workflows on Google Cloud
Coding agent from OpenAI that runs locally on your computer
Minimal, extensible agent harness that you can make your own
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Category
CLI agentGemini CLI family
CLI agentCodex family
CLI agent
CLI agentTrae family
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Not yet checked
Not yet checked
Not yet checked
Plans
Not yet checked
Not yet checked
Runs on
Linux
Yes
Yes
Yes
Not yet checked
Terminal
Yes
Yes
Yes
Yes
Windows
Not yet checked
Yes
Yes
Not yet checked
macOS
Yes
Yes
Yes
Not yet checked
Models and agents
Model providers
Google
OpenAIGoogleOllamaAmazon BedrockLM Studio
OpenAIAnthropicOpenRouterGoogleOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+29 more model providers
LM StudioMoonshot AIGroqZ.aiMistralFireworksMiniMaxGitHub CopilotOpenCode GoTogether AIvLLMAzure OpenAIHugging FaceVercel AI GatewayCerebrasOpenCode Console (OpenCode Zen)llama.cppAlibaba (Qwen)XiaomiNVIDIABasetenCloudflare Workers AIMeta AI (Llama)Cloudflare AI GatewayMicrosoft Foundry (Azure AI Foundry)TypeSafe AIAnt LingRadiusSGLang
Not yet checked
Models
Google Gemini
OpenAIGPT-6.2 AstraGPT-6.2 SolGPT-6.1 TerraGPT-6.1 SolGPT-6 Luna
AnthropicOpenAIDeepSeekNVIDIA NIMGoogle GeminiMistralGroqCerebrasxAIOpenRouterVercel AI GatewayMiniMaxMoonshot AIQwenMetaHugging FaceFireworksTogether AIBaseten
Not yet checked
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
12
32Most
19
0
Release days per week
None in 26 weeks
Latest release, any channel
v0.68.0 10 Nov 2026
v1.5.2 10 Nov 2026
Not yet checked
Index score
Score and rank
44 #18 Score 44.3; ranked on the unrounded score
91 #2 Score 90.7; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
Not enough data yet
Mindshare
4458 Hacker News mentions in the last 90 days
914,237 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
Adoption, not scored
95108,907 stars, read 18 Nov 2026
97135,675 stars, read 18 Nov 2026
96122,575 stars, read 18 Nov 2026
7712,205 stars, read 18 Nov 2026
Votes
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Not ranked
Full page

Watch Gemini CLI vs Codex CLI vs Pi vs Trae Agent on YouTube

More comparisons

Build your own