GitHub - cachebag/jumpy: Sweet-spot between trad programming and AI-assisted programming. · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
cachebag
jumpy
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
master
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>15 Commits<br>15 Commits
.github/workflows
.github/workflows
lua/jumpy
lua/jumpy
plugin
plugin
tests
tests
.luacheckrc
.luacheckrc
LICENSE
LICENSE
Makefile
Makefile
README.md
README.md
stylua.toml
stylua.toml
View all files
Repository files navigation
jumpy
Inspired by 99: I, like Prime, wanted a tool to allow for me to still be in the driver seat if I am going to spawn an AI to edit my code.
The main difference between jumpy and other tools, like 99, are:
feature<br>jumpy<br>avante / sidekick<br>codecompanion inline<br>claude code / aider
Interaction model<br>Inline prompt → hunks in buffer<br>Sidebar chat → apply<br>Inline edit → accept/reject<br>CLI agent → full file writes
Review granularity<br>Per-hunk accept/reject<br>Per-file or per-suggestion<br>Per-change<br>Post-hoc (git diff)
Context switch<br>None: you stay in buffer<br>Sidebar opens<br>Minimal<br>Leave editor or split terminal
LLM output format<br>Search/replace blocks<br>Full file / patch<br>Full file<br>Full file via temp
Token efficiency<br>High (only changed lines sent back)<br>Lower (full context)<br>Lower<br>Lower
Scope<br>Single targeted edit<br>Multi-file refactors, chat<br>Single edit or chat<br>Whole-project agentic tasks
Some of these are to be fleshed out, but the sole purpose is to know exactly what I am letting the LLM write into my code. I have no interest in letting it change everything, and only then can I go back and review every change.
So the philosophy here is: yes, I still want to handwrite my code AND use AI, but I prefer that I have full control over what the AI is writing. I don't want to have to wait until it finishes in order to review its changes.
That being said, I don't know wtf I'm doing , and right now, this really doesn't work very well.
But hopefully it will soon :P
Install
-- lazy.nvim<br>"cachebag/jumpy",<br>config = function()<br>require("jumpy").setup({<br>provider = "anthropic", -- or "openai", "openrouter"<br>})<br>end,
set your API key: export ANTHROPIC_API_KEY="sk-ant-..." (or OPENAI_API_KEY, JUMPY_API_KEY for openrouter).
Use
Keybind<br>Action
Open prompt, type your change, hit
]h / [h<br>Next / previous hunk
Accept hunk
Reject hunk
Accept all hunks
Reject all hunks
Reprompt the hunk under cursor
License
MIT
About
Sweet-spot between trad programming and AI-assisted programming.
Resources
Readme
License
MIT license
Uh oh!
There was an error while loading. Please reload this page.
Activity
Stars
stars
Watchers
watching
Forks
forks
Report repository
Releases
No releases published
Contributors
cachebag<br>akrm
Languages
Lua<br>99.3%
Other<br>0.7%
You can’t perform that action at this time.