Skip to content
ADE Index

Hermes Agent vs OpenCode vs SWE-agent vs ucode

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SWE-agent has been superseded by mini-SWE-agent: Most of our current development effort is on mini-swe-agent, 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 which has superseded SWE-agent.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

Pick this if…

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

Checked for Hermes Agent, OpenCode and SWE-agent, not yet for ucode: Price (Hermes Agent: ; OpenCode: ; SWE-agent: ), Bring your own key (Hermes Agent: ; OpenCode: ; SWE-agent: )

Checked for OpenCode and ucode, not yet for Hermes Agent and SWE-agent: Systems (OpenCode: , ; ucode: , , , )

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 ucode’s capabilities yet. 24 capabilities are checked for at least two of these tools. 5 differ only in a limit. 8 others are checked for one tool only.

Differences only5
  • 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

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
,,,,,,,,
+2 more model providers
,
Not every provider checked yet
Listing also names: SpaceXSI (Grok), GitHub Copilot
,,,,,,,,
+67 more model providers
,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,
+ providers you addNot every provider checked yetSWE-agent reaches 75 of these only through LiteLLM’s provider list ·
Listing also names 14 othersSpaceXSI (Grok), Alibaba (Qwen), Meta AI (Llama), Microsoft Foundry (Azure AI Foundry), Nebius Token Factory (Nebius AI Studio), CoreWeave (Weights & Biases), Helicone AI Gateway, AI21 Labs, OCI Enterprise AI (OCI Generative AI), Amazon SageMaker AI (SageMaker), Apertis (Stima API), Public AI, Heroku Managed Inference and Agents, NVIDIA Dynamo-Triton (Triton Inference Server)
Listing names: Google
Local modelsNot yet checked: SWE-agent, ucode
Not yet checked for SWE-agent
Not yet checked for ucode
Custom OpenAI-compatible endpointNot yet checked: SWE-agent, ucode
Not yet checked for SWE-agent
Not yet checked for ucode
Token and cost usageNot yet checked: SWE-agent, ucode
Not yet checked for SWE-agent
Not yet checked for ucode

MCP, hooks, skills and subagents

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

Editors, scripts and CI

Editor integrationNot yet checked: SWE-agent, ucode
ACP editors
ACP clients such as Zed
Not yet checked for SWE-agent
Not yet checked for ucode
Headless modeNot yet checked: SWE-agent, ucode
Not yet checked for SWE-agent
Not yet checked for ucode
JSON outputNot yet checked: SWE-agent, ucode
Not yet checked for SWE-agent
Not yet checked for ucode

Review, steer and undo

Plan modeNot yet checked: Hermes Agent, SWE-agent, ucode
Not yet checked for Hermes Agent
Not yet checked for SWE-agent
Not yet checked for ucode
Read-only modeNot yet checked: Hermes Agent, SWE-agent, ucode
Not yet checked for Hermes Agent
Plan profile; shell still asks
Not yet checked for SWE-agent
Not yet checked for ucode
Review diffsNot yet checked: SWE-agent, ucode
Needs checkpoints on
In ACP permission requests
Not yet checked for SWE-agent
Not yet checked for ucode
Undo file editsNot yet checked: SWE-agent, ucode
Opt-in; local and SSH only
Not yet checked for SWE-agent
Not yet checked for ucode

Parallel agents

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

Context and memory

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

Remote and mobile control

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

Sandbox, permissions and privacy

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

Images, web and your computer

Image inputNot yet checked: SWE-agent, ucode
Needs an image-capable model
Not yet checked for SWE-agent
Not yet checked for ucode
Fetch URLsNot yet checked: Hermes Agent, SWE-agent, ucode
Not yet checked for Hermes Agent
Not yet checked for SWE-agent
Not yet checked for ucode
Browser automationNot yet checked: OpenCode, SWE-agent, ucode
Not yet checked for OpenCode
Not yet checked for SWE-agent
Not yet checked for ucode
Voice inputNot yet checked: OpenCode, SWE-agent, ucode
Not yet checked for OpenCode
Not yet checked for SWE-agent
Not yet checked for ucode
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

Hermes Agent

OpenCode

SWE-agent

ucode

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48OpenCode79SWE-agent8ucodeNot enough data yet

Mindshare HN mentions, 90 days

Hermes Agent84OpenCode1,414SWE-agent1ucode0

Adoption GitHub stars, not scored

Hermes Agent264kOpenCode228kSWE-agent20.8kucode2

Release days last 90 days

Hermes Agent19OpenCode28SWE-agent0ucode9

Lowest monthly plan billed monthly, lower is cheaper

Hermes AgentNot yet checkedOpenCode$10/monthSWE-agentNot yet checkeducodeNot yet checked

Platforms systems and surfaces

Hermes AgentNot yet checkedOpenCode3SWE-agent1ucode4

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
Hermes AgentCLI agent
OpenCodeAnomaly · CLI agent
SWE-agentDeprecatedPrinceton University and Stanford University · CLI agent
ucodesppideey · CLI agent
Interface
Terminal UI with an inline diff, passing bun tests and a context sidebar
What it is
Terminal agent for writing, reviewing and running code in local projects
Coding agent with switchable build and read-only plan agents
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice.
Free, open-source AI coding agent for your terminal.
Category
CLI agent
CLI agent
CLI agentDeprecated
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
Yes
Not yet checked
Runs on
Linux
Not yet checked
Not yet checked
Not yet checked
Yes
Terminal
Not yet checked
Yes
Yes
Yes
Web
Not yet checked
Yes
Not yet checked
Not yet checked
Windows
Not yet checked
Yes
Not yet checked
Yes
macOS
Not yet checked
Not yet checked
Not yet checked
Yes
Models and agents
Models
Not yet checked
Not yet checked
GPT-4oClaude Sonnet 4
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
19
28Most
0
9
Release days per week
None in 26 weeks
Latest release, any channel
v2.3.2 18 Nov 2026
v1.1.0 22 May 2025
v1.68.1 6 Oct 2026
Index score
Score and rank
48 #14 Score 48.2; ranked on the unrounded score
79 #3 Score 78.8; ranked on the unrounded score
8 #153 DeprecatedScore 7.5; ranked on the unrounded score
Not enough data yet
Mindshare
4884 Hacker News mentions in the last 90 days
791,414 Hacker News mentions in the last 90 days
81 Hacker News mention in the last 90 days
00 Hacker News mentions in the last 90 days
Adoption, not scored
100264,230 stars, read 18 Nov 2026
100227,631 stars, read 18 Nov 2026
8120,825 stars, read 18 Nov 2026
92 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 Hermes Agent vs OpenCode vs SWE-agent vs ucode on YouTube

More comparisons

Build your own