Skip to content
ADE Index

mini-SWE-agent vs hax

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

How they differ

Model providersmini-SWE-agent 4 · hax 8 · 3 in common
Prisma AIRS AI Gateway (Portkey)
,,OpenCode Go,OpenCode Console (OpenCode Zen),
Show 3 shared
,,
Pick this if…

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

Sourced for hax, not yet checked for mini-SWE-agent: Editors and systems (, , , )

Same for both (2): Price: Free (open source) · Bring your own key: Yes
  • Price: Free (open source) ·
  • Bring your own key: Yes ·

Not yet checked for either tool: agents it runs.

Provider names use the same listing as each tool page. Dotted values open their quote. A capability not shown is not yet sourced; the tool may still have it.

About these tools

mini-SWE-agent

hax

How to read the Index score

At a glance

Index score out of 100

mini-SWE-agent21hax23

Mindshare HN mentions, 90 days

mini-SWE-agent6hax7

Adoption GitHub stars, not scored

mini-SWE-agent9.7khax1k

Release days last 90 days

mini-SWE-agent0hax5

Platforms listed surfaces

mini-SWE-agent1hax4

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

2 of 4
mini-SWE-agentSWE-agent · CLI agent
haxOleksandr Chekhovskyi · CLI agent
Interface
mini-SWE-agent interface
hax interface
What it is
The 100 line AI agent that solves GitHub issues or helps you in your command line.
A minimalist, terminal-native coding agent written in C.
Category
CLI agent
CLI agent
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Plans
Bring your own key
Yes
Yes
Runs on
Linux
Not yet checked
Yes
Terminal
Yes
Yes
Windows
Not yet checked
Yes
macOS
Not yet checked
Yes
Models and agents
Model providers
AnthropicOpenAIOpenRouterPrisma AIRS AI Gateway (Portkey)
AnthropicOpenAIOllamaOpenRouterDeepSeekOpenCode GoOpenCode Console (OpenCode Zen)llama.cpp
Models
AnthropicOpenAIOpenRouterPortkey
OpenAIAnthropicOpenRouteropencode-zenopencode-goDeepSeekllama.cppOllama
Drives these agents
Not yet checked
Not yet checked
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
0
5
Release days per week
Latest release, any channel
v2.4.6 23 Jul 2026
v0.7.0 12 Nov 2026
Index score
Score and rank
21 #70 Score 21.1; ranked on the unrounded score
23 #64 Score 22.6; ranked on the unrounded score
Mindshare
216 Hacker News mentions in the last 90 days
237 Hacker News mentions in the last 90 days
Adoption, not scored
759,713 stars, read 18 Nov 2026
571,005 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.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch mini-SWE-agent vs hax on YouTube

More comparisons

Build your own