Skip to content
ADE Index

Hermes Agent vs Pi vs pool

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

How they differ

Pick this if…

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

Checked for Hermes Agent and Pi, not yet for pool: Price (Hermes Agent: ; Pi: ), Bring your own key (Hermes Agent: ; Pi: )

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

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.

We have not checked pool’s capabilities yet. 19 capabilities are checked for at least two of these tools. 4 get different answers: Approval modes, Subagents, Undo file edits and Notifications; 2 differ only in a limit. 14 others are checked for one tool only.

Differences only6
  • 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

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)
Local modelsNot yet checked: pool
Not yet checked for pool
Custom OpenAI-compatible endpointNot yet checked: pool
Not yet checked for pool
Token and cost usageNot yet checked: pool
Not yet checked for pool

MCP, hooks, skills and subagents

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

Editors, scripts and CI

Editor integrationNot yet checked: Pi, pool
ACP editors
Not yet checked for Pi
Not yet checked for pool
Headless modeNot yet checked: pool
Not yet checked for pool
JSON outputNot yet checked: pool
Not yet checked for pool

Review, steer and undo

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

Parallel agents

Parallel sessionsNot yet checked: Pi, pool
Not yet checked for Pi
Not yet checked for pool
Git worktreesNot yet checked: Pi, pool
Not yet checked for Pi
Not yet checked for pool

Context and memory

Project instruction filesNot yet checked: pool
Not yet checked for pool
Memory across sessionsNot yet checked: Pi, pool
Not yet checked for Pi
Not yet checked for pool
Resume a sessionNot yet checked: pool
Not yet checked for pool
Browse past sessionsNot yet checked: pool
Not yet checked for pool

Remote and mobile control

Remote controlNot yet checked: Pi, pool
Not yet checked for Pi
Not yet checked for pool
Steer from a phoneNot yet checked: Pi, pool
Unblocks Kanban workers
Not yet checked for Pi
Not yet checked for pool
NotificationsNot yet checked: pool
Maker's notify example
Not yet checked for pool

Sandbox, permissions and privacy

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

Images, web and your computer

Image inputNot yet checked: pool
Needs a compatible terminal
Not yet checked for pool
Browser automationNot yet checked: Pi, pool
Not yet checked for Pi
Not yet checked for pool
Voice inputNot yet checked: Pi, pool
Not yet checked for Pi
Not yet checked for pool
Not yet checked: , ,

4 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

pool

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48Pi78poolNot enough data yet

Mindshare HN mentions, 90 days

Hermes Agent84Pi1,310pool0

Adoption GitHub stars, not scored

Hermes Agent264kPi123kpool446

Release days last 90 days

Hermes Agent19Pi19pool0

Platforms systems and surfaces

Hermes AgentNot yet checkedPi4pool4

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
poolpoolsideai · CLI agent
Interface
pi startup listing loaded context, skills and extensions, then reading docs and running bash
What it is
Terminal agent for writing, reviewing and running code in local projects
Minimal, extensible agent harness that you can make your own
pool is Poolside’s coding agent that runs in your terminal or integrates with any ACP-compatible editor
Category
CLI agent
CLI agent
CLI agent
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
Plans
Not yet checked
Bring your own key
Yes
Yes
Not yet checked
Runs on
Linux
Not yet checked
Yes
Yes
Terminal
Not yet checked
Yes
Yes
Windows
Not yet checked
Yes
Yes
macOS
Not yet checked
Yes
Yes
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
0
Release days per week
Latest release, any channel
v1.5.2 10 Nov 2026
v1.0.16 14 Aug 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
Not enough data yet
Mindshare
4884 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
100264,230 stars, read 18 Nov 2026
96122,575 stars, read 18 Nov 2026
50446 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
Not ranked
Full page

Watch Hermes Agent vs Pi vs pool on YouTube

More comparisons

Build your own