Skip to content
ADE Index

Hermes Agent vs psi vs SWE-agent

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

How they differ

SWE-agent has been superseded by mini-SWE-agent: Most of our current development effort is on mini-swe-agent, > which has superseded SWE-agent. raw.githubusercontent.com

Pick this if…

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

Checked for psi, not yet for Hermes Agent and SWE-agent: Systems (, , )

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.

We have not checked psi’s capabilities yet. One capability is checked for at least two of these tools. One differs only in a limit. 28 others are checked for one tool only.

Differences only1
  • Yesthe maker documents it
  • *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
,,,
Listing also names: Moonshot AI
Listing names: Anthropic
Local modelsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Custom OpenAI-compatible endpointNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Token and cost usageNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent

MCP, hooks, skills and subagents

MCP serversNot yet checked: psi, SWE-agent
local and remote
Not yet checked for psi
Not yet checked for SWE-agent
HooksNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
SkillsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
SubagentsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
PluginsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Custom commandsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent

Editors, scripts and CI

Editor integrationNot yet checked: psi, SWE-agent
ACP editors
Not yet checked for psi
Not yet checked for SWE-agent
Headless modeNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
JSON outputNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent

Review, steer and undo

Review diffsNot yet checked: psi, SWE-agent
Needs checkpoints on
Not yet checked for psi
Not yet checked for SWE-agent
Undo file editsNot yet checked: psi, SWE-agent
Opt-in; local and SSH only
Not yet checked for psi
Not yet checked for SWE-agent

Parallel agents

Parallel sessionsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Git worktreesNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent

Context and memory

Project instruction filesNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Memory across sessionsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Resume a sessionNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Browse past sessionsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent

Remote and mobile control

Remote controlNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Steer from a phoneNot yet checked: psi, SWE-agent
Unblocks Kanban workers
Not yet checked for psi
Not yet checked for SWE-agent
NotificationsNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent

Sandbox, permissions and privacy

Approval modesNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Runs in a containerNot yet checked: psi
Official Docker setup
Not yet checked for psi
Needs Docker

Images, web and your computer

Image inputNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Browser automationNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Voice inputNot yet checked: psi, SWE-agent
Not yet checked for psi
Not yet checked for SWE-agent
Not yet checked: , ,

8 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

psi

SWE-agent

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48psi8SWE-agent8

Mindshare HN mentions, 90 days

Hermes Agent84psi1SWE-agent1

Adoption GitHub stars, not scored

Hermes Agent264kpsiNo public repositorySWE-agent20.8k

Release days last 90 days

Hermes Agent19psiNot yet checkedSWE-agent0

Platforms systems and surfaces

Hermes AgentNot yet checkedpsi3SWE-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
3 of 4
Hermes AgentCLI agent
psiCLI agent
SWE-agentDeprecatedPrinceton University and Stanford University · CLI agent
Interface
What it is
Terminal agent for writing, reviewing and running code in local projects
Coding agent distributed as a portable binary
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice.
Category
CLI agent
CLI agent
CLI agentDeprecated
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
Not yet checked
Yes
Windows
Not yet checked
Yes
Not yet checked
macOS
Not yet checked
Yes
Not yet checked
Models and agents
Models
Not yet checked
Not yet checked
GPT-4oClaude Sonnet 4
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
Not yet checked
GitHub stars
Most
No public repository
Release days, last 90 days
19
Not yet checked
0
Release days per week
Not yet checked
Latest release, any channel
Not yet checked
v1.1.0 22 May 2025
Index score
Score and rank
48 #14 Score 48.2; ranked on the unrounded score
8 #154 Score 7.5; ranked on the unrounded score
8 #154 DeprecatedScore 7.5; ranked on the unrounded score
Mindshare
4884 Hacker News mentions in the last 90 days
81 Hacker News mention in the last 90 days
81 Hacker News mention in the last 90 days
Adoption, not scored
100264,230 stars, read 18 Nov 2026
No public repository
8120,825 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 psi vs SWE-agent on YouTube

More comparisons

Build your own