Ape

Ape is an AI for Linux commands.

ape "Find all the important PDF files in user/projects. An important PDF file has 'attention' in its name. Write the results to important_files.txt and then move it to Documents."

Output:

find ~/user/projects -type f -name "*attention*.pdf" > important_files.txt && mv important_files.txt ~/Documents/

Ape works with the following providers supported by Pydantic AI: OpenAI, Anthropic, Google, Groq, and Mistral.

To install (uv recommended):

uv tool install ape-linux

Next, choose a model with APE_MODEL in provider:name form (see the Pydantic AI docs for the supported providers and models) and set your provider API key in APE_API_KEY. Ape infers the provider from the model name and passes this key straight to it, so APE_API_KEY must be a key for that model's provider. Ape uses its own key variable rather than a provider's standard one (like OPENAI_API_KEY), so setting it up for Ape doesn't affect other tools on your system:

export APE_MODEL=openai:gpt-5.4-nano
export APE_API_KEY=key

Both are required.

To run:

ape Create a symbolic link called win pointing to /mnt/c/Users/jdoe

Output:

ln -s /mnt/c/Users/jdoe win

Another example:

ape Delete all the .venv directories under projects/

Output:

find projects/ -type d -name ".venv" -exec rm -rf {} +

If you ask for something that isn't a Linux command task:

ape Tell me about monkeys

Ape prints a short explanation to standard error and exits with status 2. Commands only ever go to standard output, so a refusal is never mistaken for one (and won't run if you pipe Ape into a shell):

ape: I can only help with Linux and Unix command-line tasks.

You can set the sampling temperature with the APE_TEMPERATURE environment variable (default 0.2). Some models — for example certain reasoning models — reject a temperature; set APE_TEMPERATURE=undefined to send none at all and let the model use its own default:

export APE_TEMPERATURE=0.7        # use a specific temperature
export APE_TEMPERATURE=undefined  # send no temperature at all

System-aware suggestions

Ape automatically detects a few facts about your machine and adds them to the prompt so the suggested command is correct for your environment — for example BSD (macOS) vs GNU (Linux) flags, the right package manager (brew, apt, dnf, pacman, ...), and tools that are actually installed. It looks at:

• operating system and version (macOS version or Linux distribution),
• whether the userland is BSD or GNU,
• CPU architecture (e.g. arm64 vs x86_64),
• your shell ($SHELL),
• whether you are root,
• available package manager(s) and common tools (rg, fd, jq, docker, ...).

This is all gathered locally with the Python standard library and is best-effort: if anything can't be determined it is simply left out. No identifying information is collected or sent — never your username, hostname, working directory, or home path.

To see exactly what Ape detects and sends (without calling the model), run ape-system-info:

ape-system-info

Output (example):

Operating system: Darwin
macOS version: 26.5
Userland: BSD (macOS) — prefer BSD-compatible flags
Architecture: arm64
Shell: /bin/zsh
Privileges: non-root (use sudo for privileged actions)
Package manager(s): brew
Available tools: rg, fd, jq, git, curl, docker, tar, rsync, sed, awk

See also: Gorilla