git-agent
git-agent writes git commit messages for your changes with a language model, either
one running on your own machine (LM Studio, Ollama, llama.cpp, vLLM) or one from a
cloud provider such as OpenAI, Anthropic or OpenRouter. You review each proposed
message, then commit it, edit it, regenerate it, or tell the model what to change.
git agent pr does the same for pull requests on GitHub.
Why I made git-agent
I made git-agent mainly to get the commit message generation from IntelliJ IDEA without running IDEA. IDEA uses nearly 3-4 GB of RAM, and I need that memory for running local language models. git-agent also has stronger automation features, for use in pipelines or with lightweight code editors. The code was developed using Gemma 4 locally, and refactored with Claude.
Install
Because the binary is called git-agent, git also runs it as git agent.
With Homebrew
Homebrew builds git-agent from source, and installs its own Rust for the build if you
don't have it yet. brew upgrade git-agent updates git-agent, and
brew uninstall git-agent removes it.
From crates.io
git-agent is published on crates.io. With Rust 1.88 or newer installed, run:
Cargo builds an optimized binary and copies it to ~/.cargo/bin/ (or
$CARGO_HOME/bin/). --locked uses the exact dependency versions the release was
tested with. Run the same command again to update to the latest release, and
cargo uninstall git-agent to remove it.
From a local checkout
To try changes that aren't released yet, install from a clone of the repository:
If you installed Rust with Homebrew or a Linux package manager
~/.cargo/bin must be on your PATH. rustup adds it for you, but Homebrew and Linux
package managers don't, so add it yourself, for example in ~/.zshrc:
Usage
Commands
Which changes are included
If you have staged changes, git-agent describes and commits only those. If nothing is
staged, it describes all changes to tracked files and commits them with
git commit --all. Untracked files are left out unless you use --all.
Reviewing the message
git-agent shows the proposed message and waits for one of these keys:
| Key | Action |
|---|---|
c |
Commit with this message |
p |
Commit with this message, then push |
e |
Open it in your git editor (GIT_EDITOR, core.editor, VISUAL, EDITOR) |
r |
Generate a new message |
f |
Tell the model what to change, e.g. f shorter, and mention the CLI flags |
q |
Quit without committing |
If the commit fails
When git commit fails, for example because a hook rejects it, git-agent saves the
message to .git/GIT_AGENT_MSG. You can reuse it with
git commit --file .git/GIT_AGENT_MSG.
Splitting a change into commits
When your changes do several things at once, git agent split turns them into
several commits. The model groups the changes by what they are for, and you review
its plan and then each commit's message.
How git-agent plans the commits
git-agent splits the changes a commit would include: the staged ones, or all changes to tracked files if nothing is staged. It cuts them into parts. A part is one hunk of a changed file, or a whole file when the file is new, deleted, renamed or binary, or excluded like a lockfile. The model sees the numbered parts and groups them into commits, ordered so that each builds on those before it. If it leaves a part out, git-agent adds that part to the commit with the rest of its file, or to a last commit, so nothing goes missing. When the hunks are too many to show the model one by one, it groups whole files instead.
Reviewing the plan
── Proposed commits ────────────────────────────────────────────
1. Introduce LRU caching for configuration loading
Cargo.lock, Cargo.toml, README.md, src/cache.rs (new file), src/config.rs (1 of 3 changes)
2. Refine config parsing logic and documentation
src/config.rs (2 of 3 changes)
────────────────────────────────────────────────────────────────
[a]ccept [e]dit [r]egenerate [f]eedback [q]uit [?] ›
a accepts the plan. e opens it in your git editor, where each part has a numbered
line under its commit; move a line to move the part to another commit. r asks for a
new plan, and f tells the model what to change, such as
f put the feature and its documentation in one commit.
Making the commits
git-agent then makes the commits in order. For each one it writes the message from
that commit's own changes, and you review it like any other message, with two
differences: c commits, and s skips the commit and leaves its changes as they
were. q stops; the commits made so far stay. Changes that aren't committed stay
where they were, staged or not, so skipping or stopping loses nothing.
git-agent doesn't build or test the commits in between, so a commit may not compile on its own if the plan separates code that belongs together. Secrets are checked as for any commit, and git-agent won't split changes while a merge or rebase is in progress.
Pushing
git-agent pushes with a plain git push, so it works with GitHub or any other remote
and uses your existing git credentials. The first time you push a branch that has no
upstream, git-agent sets one: it uses remote.pushDefault if you've configured it,
otherwise your only remote, otherwise origin. If the repository has no remote yet,
create one on GitHub with gh repo create --source . --push.
If the push fails, the commit stays. Fix the problem and run git push.
When the remote has new commits
Before pushing, git-agent fetches from the remote. If the remote has commits you don't
have, such as a file you edited on GitHub, it lists them and rebases your commit on
top of them. Your history stays linear and the remote commits stay as they are. From
the review menu, git-agent asks before it rebases; --commit --push rebases without
asking. Any uncommitted changes are set aside during the rebase and restored
afterwards.
Conflicts
If your commit conflicts with the remote commits, git-agent cancels the rebase and
leaves your branch as it was. Run git pull --rebase, resolve the conflicts, then run
git push. git-agent never force-pushes.
Pull requests
git agent pr writes a title and description for the current branch from its
commits and its diff, then creates the pull request on GitHub. The pull request
merges into the repository's default branch unless you name another with --base.
git-agent fetches that branch first, so commits that reached it from elsewhere aren't
described as yours.
Reviewing the pull request
The first line of the proposal is the title, and the rest is the description in
Markdown. The review works like the one for commit messages, except for its first two
keys: c creates the pull request and d creates it as a draft. If the branch isn't
on GitHub yet, or GitHub lacks some of its commits, git-agent pushes it first, the
same way it pushes after a commit. Uncommitted changes are not part of the pull
request, and git-agent tells you when you have some.
What it needs
git-agent creates pull requests with the GitHub CLI, so it
uses your existing GitHub login. Install gh and run gh auth login once. Only
--raw together with --base works without it.
If the branch already has an open pull request, git-agent shows its address and
stops. If gh pr create fails, git-agent saves the description to
.git/GIT_AGENT_PR.md and prints the command that creates the pull request from it.
Choosing a model
git-agent sends your changes to the model server at base_url. By default that is
http://localhost:1234/v1, the address of LM Studio running on your own machine.
To use another local server, such as Ollama, or a cloud provider, choose it in
git agent config or change base_url in the config file.
Local servers
With a local server, you don't have to configure a model. git-agent asks the server
which model is loaded and uses that one. If several models are loaded, or none is and
the server has more than one, git-agent asks you to pick one with git agent config
or --model. git agent models lists the server's models and marks the one
git-agent uses.
Cloud providers
git-agent works with any provider that has an OpenAI-compatible API, and with Anthropic through its own Messages API. Your diffs then leave your machine and go to that provider, without the secrets git-agent finds in them.
To set one up, run git agent config, choose Provider, and pick it from the list:
OpenAI, Anthropic, OpenRouter, Google Gemini, Mistral, Groq, DeepSeek, xAI, Together
AI, Fireworks AI or Cerebras. "Other" takes the address of any other OpenAI-compatible
API. git-agent asks for your API key, then lists the provider's models for you to pick
from. You can type to filter the list.
Most providers don't report a model's context window, so the menu asks for it after you pick a model. You'll find it on the provider's model page. Without it, git-agent assumes 4,096 tokens and shortens large diffs much more than it needs to. Anthropic and OpenRouter report it, so the menu doesn't ask for their models.
You can also set the provider in the config file:
= "https://api.example.com/v1" # the provider's OpenAI-compatible endpoint
= "model-id" # an ID from `git agent models`
= 128000 # from the provider's model documentation
API keys
git-agent never stores API keys in the config file. On macOS, git agent config
saves each key in your keychain, under the name git-agent and the provider's host
(such as api.openai.com), and git-agent reads it from there on every run. Each
provider keeps its own key, so you can switch between them. After you install a new
version of git-agent, macOS may ask whether git-agent can use the saved key; choose
Always Allow.
On other systems, set the GIT_AGENT_API_KEY environment variable. It also works on
macOS, and like --api-key, it overrides a saved key:
Secrets in your changes
Before git-agent sends anything to the model, it looks for secrets in it and replaces
each one with [REDACTED]. That covers the diff and, for pull requests, the commit
messages. The model still sees that something was there, but the secret itself never
goes into a prompt, whichever server you use.
Rejecting or warning
By default, git-agent also refuses to commit or push secrets. When your changes add one, it stops before it asks the model and lists what it found:
error: the changes add what look like secrets, so git-agent didn't commit them:
.env:2 DB_PASSWORD value
src/client.rs:14 GitHub token
Take them out of the changes. If they aren't real secrets, add --on-secrets warn, or choose Warn under Secrets in `git agent config`.
Before every push, git-agent checks each commit the push would send, including its
message, because a secret that a later commit removes is still in the history.
git agent pr checks every commit on the branch the same way before it writes the
pull request. A secret on a line that your change leaves alone or removes doesn't stop
anything; git-agent only lists it.
To be warned instead, set on_secrets = "warn" in the config file, choose Warn under
Secrets in git agent config, or pass --on-secrets warn for one run. git-agent then
lists the secrets and carries on, and the model still gets [REDACTED] in their place.
What git-agent recognizes
- API keys and tokens in the formats of GitHub, GitLab, Slack, Stripe, AWS, OpenAI, Anthropic, Google, Hugging Face, Groq, xAI, npm and PyPI, and JSON web tokens
- private keys (
-----BEGIN … PRIVATE KEY-----) - passwords in URLs, such as
postgres://app:s3cret@db.example.com, and bearer tokens - values assigned to names such as
password,secret,tokenorAPI_KEY, in.envfiles, YAML, JSON or code
It leaves placeholders such as your-api-key and changeme alone, and references
such as ${API_KEY} too. A secret in a format git-agent doesn't know can still get
through.
Large changes
Each run starts with a line that names the model and shows how much of its context the prompt uses:
🤖 google/gemma-4-e4b (loaded on the server) · prompt about 24,578 of 131,072 context tokens
Context window
git-agent asks the server how large the model's context window is, so it knows how
much of your changes it can send. LM Studio, Ollama, llama.cpp, vLLM, Anthropic and
OpenRouter report it. For other servers, and for models that aren't loaded yet,
git-agent assumes 4,096 tokens and tells you so. Set context_length to give it the
real size.
Large prompts take longer to process. To keep them smaller, set context_length
below the model's real context.
How git-agent shortens a diff
The prompt always leaves room for the reply. When your changes don't fit, git-agent shortens them in steps and stops as soon as they fit:
- It leaves out the unchanged lines that git shows around each change.
- It shares the remaining room between the files. Files with small diffs are sent whole and larger ones are cut short, so every file shows at least its first changes.
- If there are too many files even for that, the largest ones are sent by name only. They still appear in the list of changed files.
What git-agent tells you
When it shortens your changes, git-agent prints what it left out:
warning: the changes need about 24,656 tokens, more than fit in the context, so git-agent sent part of them:
46 of 58 files in full, without the unchanged lines around the changes
12 cut short: src/builder/arg.rs (6 of 23 changed lines), src/builder/command.rs (6 of 93 changed lines), and 10 more
The message may then miss details from the shortened files. For better messages,
commit in smaller parts: git agent split does
that for you, or you can stage some of the files, run git agent, and repeat.
Loading the model with a larger context also helps.
Configuration
Changing settings
Run git agent config to change settings in a menu:
git-agent settings · ~/.config/git-agent/config.toml
? Setting:
> Provider LM Studio · http://localhost:1234/v1
Model automatic: the model loaded on the server
API key none (local servers usually need none)
Context length automatic: asked from the server
Output limit 16,000 tokens (sent only to Anthropic)
Temperature automatic: 0.4 on local servers
Timeout 300 seconds
Secrets reject: don't commit or push them
Excluded files common lockfiles
System prompt default: Conventional Commits
Done
Move with the arrow keys and press Enter to change a setting. git-agent saves each
change to the config file right away. Esc goes back one step, and quits from the main
menu. Excluded files and the system prompt open in your git editor. The menu writes
the same commented file as git agent config init, so comments you added to the file
yourself are not kept.
These commands work with the settings too:
Where settings come from
Settings come from these sources, and later ones override earlier ones:
- Built-in defaults
- The config file:
~/.config/git-agent/config.toml(or$XDG_CONFIG_HOME/git-agent/config.toml) - Environment variables
- Command-line flags
API keys come from --api-key, then GIT_AGENT_API_KEY, then the macOS keychain.
Settings
| Key | Flag | Environment variable | Default |
|---|---|---|---|
base_url |
--base-url |
GIT_AGENT_BASE_URL |
http://localhost:1234/v1 |
model |
-m, --model |
GIT_AGENT_MODEL |
the model loaded on the server |
| (API key) | --api-key |
GIT_AGENT_API_KEY |
the macOS keychain, never the file |
context_length |
--context-length |
GIT_AGENT_CONTEXT_LENGTH |
reported by the server, or 4096 |
max_output_tokens |
--max-output-tokens |
GIT_AGENT_MAX_OUTPUT_TOKENS |
16000 |
temperature |
-t, --temperature |
0.4 on local servers, else the provider's default | |
on_secrets |
--on-secrets |
GIT_AGENT_ON_SECRETS |
reject (or warn) |
timeout_secs |
300 |
||
exclude |
common lockfiles | ||
system_prompt |
Conventional Commits instructions | ||
| (file location) | --config |
GIT_AGENT_CONFIG |
see above |
Temperature
On local servers, git-agent uses a temperature of 0.4 unless you set another one, because a low temperature gives more predictable messages. Many cloud models accept only their default temperature and reject requests that set another one, so with a cloud provider git-agent sends a temperature only if you set one. When you switch to a cloud provider, the menu offers to stop sending it. Anthropic's API takes no temperature, so git-agent never sends one there.
Output limit
Anthropic's API needs a limit on how many tokens the model may write in one reply.
git-agent asks for at most 16,000, which leaves current models plenty of room to think
before they write the message. To change it, use "Output limit" in git agent config,
max_output_tokens in the config file, or --max-output-tokens. Much higher limits
can make a reply take longer than the timeout. OpenAI-compatible servers use their own
limit.
Using another model for one run
Flags and environment variables apply to a single run:
GIT_AGENT_BASE_URL=http://localhost:11434/v1 Notes
- Files matching
exclude(by defaultCargo.lock,package-lock.jsonand similar) appear in the list of changed files sent to the model, but their diffs don't. Deleted files are sent by name, without their old content. - git-agent removes reasoning blocks (
<think>…</think>) and code fences around the model's reply. - Set
NO_COLORto turn off colored output.
Contributing
Contributions are welcome! Open an issue for bugs and feature ideas, or send a pull request. For larger changes, please open an issue first so we can discuss the approach.
Before you send a pull request
Make sure these pass:
The tests create temporary git repositories and don't need a running model server.
License
git-agent is licensed under the MIT License. By contributing, you agree that your contributions are licensed under the same terms.