Skip to content
ADE Index

Hermes Agent vs killi vs OpenCode

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

How they differ

Pick this if…

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

Sourced for Hermes Agent, not yet for killi and OpenCode: Price ()

Sourced for Hermes Agent and killi, not yet for OpenCode: Model providers (Hermes Agent: , , , , , ; killi: , )

Sourced for Hermes Agent and OpenCode, not yet for killi: Bring your own key (Hermes Agent: ; OpenCode: )

Sourced for killi and OpenCode, not yet for Hermes Agent: Editors and systems (killi: , , ; OpenCode: , )

None of these tools has a sourced value yet for: agents it runs.

Dotted values open their quote. A capability not shown is not yet sourced; the tool may still have it.

About these tools

Hermes Agent

killi

OpenCode

How to read the Index score

At a glance

Index score out of 100

Hermes Agent48killiNot enough data yetOpenCode79

Mindshare HN mentions, 90 days

Hermes Agent84killi0OpenCode1,414

Adoption GitHub stars, not scored

Hermes Agent264kkilli56OpenCode228k

Release days last 90 days

Hermes Agent19killi1OpenCode28

Platforms listed surfaces

Hermes AgentNot yet verifiedkilli3OpenCode3

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

3 of 4
Hermes AgentCLI agent
killitimwuhaotian · CLI agent
OpenCodeAnomaly · 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
Open-source AI coding agent for your terminal, written in Rust.
Coding agent with switchable build and read-only plan agents
Category
CLI agent
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Not yet verified
Not yet verified
Not yet verified
Lowest monthly plan
Not yet verified
Not yet verified
Not yet verified
Free tier
Not yet verified
Not yet verified
Plans
  • Open-source softwareFree
Not yet verified
Not yet verified
Bring your own key
Yes
Not yet verified
Yes
Runs on
Linux
Not yet verified
Yes
Not yet verified
Terminal
Not yet verified
Not yet verified
Yes
Web
Not yet verified
Not yet verified
Yes
Windows
Not yet verified
Yes
Yes
macOS
Not yet verified
Yes
Not yet verified
Models and agents
Model providers
AnthropicOpenRouterFireworksZ.aiMoonshot AIMiniMaxxAI
OpenAIAnthropic
Not yet verified
Models
Nous PortalOpenAI CodexAnthropicOpenRouterFireworks AINovitaAIAI GatewayGLMKimiMiniMaxxAIQwen Cloud
OpenAIAnthropic
Not yet verified
Drives these agents
Not yet verified
Not yet verified
Not yet verified
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
19
1
28Most
Release days per week
Latest release, any channel
v0.7.1 18 Nov 2026
v2.3.2 18 Nov 2026
Index score
Score and rank
48 #14 Score 48.2; ranked on the unrounded score
Not enough data yet
79 #3 Score 78.8; ranked on the unrounded score
Mindshare
4884 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
791,414 Hacker News mentions in the last 90 days
Adoption, not scored
100264,230 stars, read 18 Nov 2026
3356 stars, read 18 Nov 2026
100227,631 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
Not ranked
First ranked 18 Nov 2026
Full page

Watch Hermes Agent vs killi vs OpenCode on YouTube

More comparisons

Build your own