llamactl
llamactl is the CLI for developing LlamaAgents apps locally and managing their LlamaCloud deployments.
For the full guide, see the LlamaAgents llamactl docs.
Installation
Install globally with uv:
uv tool install -U llamactl
Or pin it to a project:
uv add --dev llamactl
Quick Start
Create or select an auth profile:
llamactl auth login
If browser login is not available, use an API key:
llamactl auth token --api-key "$LLAMA_CLOUD_API_KEY" --project "$LLAMA_AGENTS_PROJECT_ID"
Scaffold and run an app:
llamactl init
cd my-app
llamactl serve
Create a cloud deployment:
llamactl deployments create
Inspect it and stream logs:
llamactl deployments get
llamactl deployments get NAME
llamactl deployments logs NAME --follow
For declarative deployments:
llamactl deployments template > deployment.yaml
llamactl deployments apply -f deployment.yaml
Command Groups
llamactl auth: log in, create API-key profiles, and switch profiles.llamactl environments: list, add, inspect, and switch LlamaCloud API environments.llamactl projects: list and select projects.llamactl organizations: list organizations.llamactl deployments: create, apply, edit, update, inspect, delete, roll back, and stream deployment logs.llamactl init: create a new LlamaAgents project from a starter template.llamactl serve: run the local app server and optional frontend dev server.llamactl pkg: generate container build files for self-hosted deployments.llamactl completion: generate or install shell completions.llamactl agentcore: run or export AgentCore apps.
Configuration
llamactl auth login and llamactl auth token create local auth profiles. A profile stores the active API environment, project, and credential used by deployment commands.
For CI and other non-interactive environments, set env vars instead of using a profile:
export LLAMA_CLOUD_API_KEY="llx-..."
export LLAMA_AGENTS_PROJECT_ID="project-id"
LLAMA_CLOUD_BASE_URL can point the CLI at a non-default environment. When both LLAMA_CLOUD_API_KEY and LLAMA_AGENTS_PROJECT_ID are set, env var auth takes precedence over the stored profile for cloud commands. Many commands also accept --project to override the active project for that invocation.
Shell Completion
Install completions for your current shell:
llamactl completion install
Or print a completion script:
llamactl completion generate zsh
Requirements
- Python 3.12+
uvfor project dependency managementgitfor cloud deployments
License
MIT
Metadata
Release files for llamactl 0.10.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llamactl-0.10.4.tar.gz | 81.3 kB | Without provenance | Details for llamactl-0.10.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llamactl-0.10.4-py3-none-any.whl | Python 3 | none | any | Details for llamactl-0.10.4-py3-none-any.whl |
Total release size: 188.1 kB
Release files / llamactl-0.10.4.tar.gz
| Download URL | llamactl-0.10.4.tar.gz |
|---|---|
| Size | 81.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9fc54158c6cb42f79d9eacc8dba0a52b7a19904c84527d50d1fb4015b59696a7
|
|
BLAKE2b-256 checksum How to use checksums |
fcd71993e8d8691bae2a12dd5b51530d7c46f7d25e17aec570d833a32e3fd0df
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.15 {"installer":{"name":"uv","version":"0.12.15","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / llamactl-0.10.4-py3-none-any.whl
| Download URL | llamactl-0.10.4-py3-none-any.whl |
|---|---|
| Size | 106.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
99adcf6dcc77862d5be12713ee4e03cd6e07f40a8a5053a52ce8d81dc5d2047d
|
|
BLAKE2b-256 checksum How to use checksums |
5c9bd59fa398716e3addf3ddd735f3832e5e3af1b23d482abf63d4e22ae112ec
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.15 {"installer":{"name":"uv","version":"0.12.15","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for llamactl 0.10.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.