How to run Aider in a cloud sandbox

Runtime runs Aider on Python 3.12 out of the box, with the model key held outside the machine. Aider's installer pins Python 3.12. That is the sandbox image's own Python, and uv is already installed. Aider's recommended uv tool install line therefore works unchanged. Each sandbox is a Firecracker microVM with its own Linux kernel and Ubuntu 24.04. The model key is a Runtime secret. The environment variable Aider reads holds a placeholder. The host's proxy adds the real key only to requests to the model API. A sandbox with 2 vCPUs and 4 GiB costs $0.03125 an hour while Aider waits on the model. aider-chat 0.86.2 was the current PyPI release on 25 October 2026.

How Aider differs from the other agents

Aider edits the files you name and the files its repository map points it to. It does not run a free-form shell loop. It runs the commands you configure, such as a test command, and sends failures back to the model. That makes it a good fit for batch jobs: the same instruction over many repos, with one sandbox for each repo.

Aider is not an MCP client, so there is one direction here: Aider running inside a Runtime sandbox.

Store the key

Aider reads Anthropic keys from ANTHROPIC_API_KEY and OpenAI keys from OPENAI_API_KEY. Store the one you use, and bind it to its API host:

Terminalprintf %s "$ANTHROPIC_API_KEY" | npx withruntime secrets set ANTHROPIC_API_KEY --host api.anthropic.com

Sandboxes in your account see the variable with a placeholder such as rtsec_3f9c…. Requests to api.anthropic.com go out with the real key. A request to any other host carries the placeholder, which is not a valid key (secrets sandboxes never see).

Script a change

TypeScriptimport { writeFile } from "node:fs/promises";import { Sandbox } from "withruntime";const repo = "https://github.com/your-org/your-repo";const message =  "Add type hints to every public function in src/billing.py and fix any test that breaks.";await using sbx = await Sandbox.create({ diskMiB: 8192, timeoutSeconds: 3600 });const install = { check: true, timeoutMs: 600_000 } as const;await sbx.exec("uv tool install --force --python python3.12 --with pip aider-chat@latest", install);await sbx.exec(["git", "clone", "--depth", "1", repo, "/workspace/app"], install);await sbx.exec("pip install -e . pytest", { ...install, cwd: "/workspace/app" });await sbx.network.set({ internet: true, allow: ["api.anthropic.com"] });const run = await sbx.exec(  [    "aider",    "--model",    "sonnet",    "--message",    message,    "--yes-always",    "--no-auto-commits",    "--no-gitignore",    "--no-check-update",    "--analytics-disable",    "--no-pretty",    "--test-cmd",    "pytest -q",    "--auto-test",    "src/billing.py",  ],  { cwd: "/workspace/app", timeoutMs: 1_800_000, onStderr: (text) => process.stderr.write(text) },);console.log(run.exitCode, run.stdout.slice(-2000));await sbx.exec("git add -A && git diff --cached -- . ':!.aider*' > /workspace/aider.patch", {  cwd: "/workspace/app",  check: true,});await writeFile("aider.patch", await sbx.files.readText("/workspace/aider.patch"));

Pythonimport sysfrom withruntime import Sandboxrepo = "https://github.com/your-org/your-repo"message = "Add type hints to every public function in src/billing.py and fix any test that breaks."with Sandbox.create(disk_mib=8192, timeout_seconds=3600) as sbx:    sbx.exec("uv tool install --force --python python3.12 --with pip aider-chat@latest",             check=True, timeout_ms=600_000)    sbx.exec(["git", "clone", "--depth", "1", repo, "/workspace/app"],             check=True, timeout_ms=600_000)    sbx.exec("pip install -e . pytest", cwd="/workspace/app",             check=True, timeout_ms=600_000)    sbx.network.set(internet=True, allow=["api.anthropic.com"])    run = sbx.exec(        ["aider", "--model", "sonnet", "--message", message, "--yes-always",         "--no-auto-commits", "--no-gitignore", "--no-check-update", "--analytics-disable",         "--no-pretty", "--test-cmd", "pytest -q", "--auto-test",         "src/billing.py"],        cwd="/workspace/app", timeout_ms=1_800_000, on_stderr=sys.stderr.write,    )    print(run.exit_code, run.stdout[-2000:])    sbx.exec("git add -A && git diff --cached -- . ':!.aider*'"             " > /workspace/aider.patch", cwd="/workspace/app", check=True)    with open("aider.patch", "w") as file:        file.write(sbx.files.read_text("/workspace/aider.patch"))

The script does the following, in order:

• uv installs Aider as a tool with its own environment. It puts aider in /workspace/.local/bin, which comes first on the sandbox's PATH. uv comes with the image, and the Python 3.12 it asks for is the system Python.
• The project's own dependencies install next, while PyPI is still reachable. That way pytest has what it needs once the network narrows.
• The network narrows to the model API. Aider also tries to fetch model metadata from GitHub at start. It continues without that metadata when the fetch fails. Add raw.githubusercontent.com to the list if you want its context-window figures current.
• --message sends one instruction, applies the edits and exits. Aider's scripting guide calls this its command-line automation mode. --message-file reads a longer instruction from a file.
• --test-cmd with --auto-test runs the tests after each edit. It gives failures back to the model to fix.
• The file list at the end adds those files to the chat. Aider's repo map finds related code on its own.
• The diff leaves out Aider's own .aider* history files. It comes back as a file, clear of the 64 KiB output cap.

Flags for scripted runs

From Aider's options reference, 25 October 2026. Each flag also has an AIDER_ environment variable, for example AIDER_YES_ALWAYS.

Aider's Python API (Coder.create) also runs inside the sandbox. Its authors say it may change without notice. The command line is the stable interface. To run the same message over many repos, fork one prepared sandbox into several copies. Each copy starts with Aider already installed.

What it costs

Runtime bills measured CPU at $0.025 per vCPU-hour, with a floor of a twentieth of a vCPU. Reserved memory is billed at $0.0075 per GiB-hour. A 2 vCPU, 4 GiB sandbox costs $0.03125 an hour while Aider waits on the model. It costs $0.08 an hour while tests keep both cores busy (pricing). The model provider bills tokens on your key. A new account gets 100 free hours of a 1 GB machine in its first 30 days. No card is needed:

Terminalnpx withruntime sandboxes run -- python3 --version

For agents that run their own shell loop, see Claude Code and OpenHands. Batch jobs over many repos are covered in agent evals and SWE-bench.

Sources

Checked 25 October 2026.

• Installation: aider-install, uv tool install --force --python python3.12 --with pip aider-chat@latest
• Scripting aider: --message, --yes-always, the Python API and its stability note
• Options reference: --auto-commits, --test-cmd, --auto-test, --check-update, --analytics-disable, environment variables
• Anthropic: ANTHROPIC_API_KEY and --list-models anthropic/
• aider/models.py: the model metadata fetched from raw.githubusercontent.com
• aider-chat on PyPI: version 0.86.2, Python 3.10 to 3.12

Facts on this page were checked on 25 October 2026.