Skip to content
ADE Index

Hermes Agent vs Pi vs Qwen Code

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

How they differ

Qwen Code is built on Gemini CLI: This project was originally based on Google Gemini CLI v0.8.2. raw.githubusercontent.com

Pick this if…

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

Checked for Pi and Qwen Code, not yet for Hermes Agent: Systems (Pi: , , , ; Qwen Code: )

Same for all 3 (1): Price: Free (open source)
  • Price: Free (open source) · ·

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

Dotted values open their quote.

What each can do

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

29 capabilities are checked for at least two of these tools. 9 get different answers, among them Approval modes, Subagents, Editor integration and Plan mode; 4 differ only in a limit. 5 others are checked for one tool only.

Differences only13
  • 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
Named model providersFrom the listing
,,,,,,,,
+30 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
Listing also names 11 othersSpaceXSI (Grok), Amazon Bedrock, Moonshot AI, Vercel AI Gateway, OpenCode Console (OpenCode Zen), Alibaba (Qwen), Meta AI (Llama), Microsoft Foundry (Azure AI Foundry), Nebius Token Factory (Nebius AI Studio), Novita AI, Command Code
,,,,,,,,
+17 more model providers
,,,,,,,,,,,,,,,,
Not every provider checked yet
Listing also names 5 othersSpaceXSI (Grok), Z.ai, OpenCode Console (OpenCode Zen), Meta AI (Llama), Microsoft Foundry (Azure AI Foundry)
,,,,,,,,
+2 more model providers
,
+ providers you add
Listing also names: Alibaba (Qwen), OCI Enterprise AI (OCI Generative AI)
Local models
Custom OpenAI-compatible endpointNot yet checked: Qwen Code
Not yet checked for Qwen Code
Token and cost usageNot yet checked: Qwen Code
Not yet checked for Qwen Code

MCP, hooks, skills and subagents

MCP servers
local and remote
local and remote
Hooks
Skills
Subagents
Not built in; Subagent example
PluginsNot yet checked: Qwen Code
Not yet checked for Qwen Code
Custom commands

Editors, scripts and CI

Editor integrationNot yet checked: Pi
ACP editors
Not yet checked for Pi
VS Code extension (beta)
Headless mode
JSON outputNot yet checked: Qwen Code
Not yet checked for Qwen Code

Review, steer and undo

Plan modeNot yet checked: Hermes Agent
Not yet checked for Hermes Agent
Not built in; Plan Mode example
Read-only modeNot yet checked: Hermes Agent
Not yet checked for Hermes Agent
Not built in; Plan Mode example
Review diffsNot yet checked: Pi, Qwen Code
Needs checkpoints on
Not yet checked for Pi
Not yet checked for Qwen Code
Undo file editsNot yet checked: Qwen Code
Opt-in; local and SSH only
Maker's git-checkpoint example
Not yet checked for Qwen Code

Parallel agents

Parallel sessionsNot yet checked: Pi, Qwen Code
Not yet checked for Pi
Not yet checked for Qwen Code
Git worktreesNot yet checked: Pi
Not yet checked for Pi

Context and memory

Project instruction files
Memory across sessionsNot yet checked: Pi
Not yet checked for Pi
Resume a session
Browse past sessions

Remote and mobile control

Remote controlNot yet checked: Pi
Not yet checked for Pi
Via chat-app Channels
Steer from a phoneNot yet checked: Pi
Unblocks Kanban workers
Not yet checked for Pi
Via chat-app Channels
NotificationsNot yet checked: Qwen Code
Maker's notify example
Not yet checked for Qwen Code

Sandbox, permissions and privacy

OS-level sandboxNot yet checked: Hermes Agent
Not yet checked for Hermes Agent
Gondolin micro-VM example
Approval modes
Runs in a containerNot yet checked: Qwen Code
Official Docker setup
The repo's Docker recipe
Not yet checked for Qwen Code
Telemetry opt-outNot yet checked: Hermes Agent
Not yet checked for Hermes Agent

Images, web and your computer

Image inputNot yet checked: Qwen Code
Needs a compatible terminal
Not yet checked for Qwen Code
Browser automationNot yet checked: Pi
Not yet checked for Pi
Needs the Chrome extension
Computer useNot yet checked: Hermes Agent, Pi
Not yet checked for Hermes Agent
Not yet checked for Pi
Add the Node REPL MCP server
Voice inputNot yet checked: Pi, Qwen Code
Not yet checked for Pi
Not yet checked for Qwen Code
Not yet checked: , ,

3 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

Hermes Agent

Pi

Qwen Code

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48Pi78Qwen Code25

Mindshare HN mentions, 90 days

Hermes Agent84Pi1,310Qwen Code9

Adoption GitHub stars, not scored

Hermes Agent264kPi123kQwen Code30.7k

Release days last 90 days

Hermes Agent19Pi19Qwen Code30

Platforms systems and surfaces

Hermes AgentNot yet checkedPi4Qwen Code2

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
3 of 4
Hermes AgentCLI agent
PiEarendil Works · CLI agent
Qwen CodeQwen · CLI agent
Interface
pi startup listing loaded context, skills and extensions, then reading docs and running bash
Terminal session editing two JS files with inline diffs, then rerunning vitest
What it is
Terminal agent for writing, reviewing and running code in local projects
Minimal, extensible agent harness that you can make your own
An open-source AI coding agent that lives in your terminal.
Category
CLI agent
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Not yet checked
Not yet checked
Free tier
Plans
Runs on
Linux
Not yet checked
Yes
Not yet checked
Terminal
Not yet checked
Yes
Yes
Web
Not yet checked
Not yet checked
Yes
Windows
Not yet checked
Yes
Not yet checked
macOS
Not yet checked
Yes
Not yet checked
Models and agents
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
19
19
30Most
Release days per week
Latest release, any channel
v1.5.2 10 Nov 2026
Index score
Score and rank
48 #14 Score 48.2; ranked on the unrounded score
78 #4 Score 77.9; ranked on the unrounded score
25 #53 Score 25.0; ranked on the unrounded score
Mindshare
4884 Hacker News mentions in the last 90 days
781,310 Hacker News mentions in the last 90 days
259 Hacker News mentions in the last 90 days
Adoption, not scored
100264,230 stars, read 18 Nov 2026
96122,575 stars, read 18 Nov 2026
8530,733 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.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch Hermes Agent vs Pi vs Qwen Code on YouTube

More comparisons

Build your own