vLLM Agentic API
Agentic API is a Rust-native gateway for OpenAI-compatible inference servers. It provides the Responses API with conversation state, tool execution, streaming, and continuation. Point it at an existing vLLM server to use open models with your applications and coding clients.
The agentic-api Python package includes the Rust gateway, the agentic CLI, and a Python launcher. The base
installation does not install vLLM or GPU dependencies.
Install
Requires Python 3.10 or newer. Prebuilt wheels are available for Linux x86_64 (glibc 2.17 or newer), macOS Intel, and macOS Apple Silicon.
python -m pip install agentic-api
python -m agentic_api --version
Start the server
With an inference server already running at http://127.0.0.1:8000:
python -m agentic_api serve --vllm-base-url http://127.0.0.1:8000
The gateway listens on port 9000 by default. Send Responses API requests to http://127.0.0.1:9000/v1/responses.
To install the pinned vLLM runtime and let the launcher manage a local inference process on a supported Linux host:
python -m pip install 'agentic-api[local]'
python -m agentic_api serve --model MODEL_ID
Run python -m agentic_api doctor --mode remote --json to check your installation.
Learn more
2 maintainers
Release files for agentic-api 0.9.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agentic_api-0.9.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl | Python 3 | none | Linux glibc 2.17+ x86-64 | Details |
| agentic_api-0.9.0-py3-none-macosx_11_0_arm64.whl | Python 3 | none | macOS 11.0+ ARM64 | Details |
| agentic_api-0.9.0-py3-none-macosx_10_12_x86_64.whl | Python 3 | none | macOS 10.12+ x86-64 | Details |
Total release size: 66.9 MB
Release files / agentic_api-0.9.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
| Download URL | agentic_api-0.9.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl |
|---|---|
| Size | 25.9 MB |
| Tags | Linux glibc 2.17+ x86-64 Python 3 |
|
SHA-256 checksum How to use checksums |
3d424fd23a9ddc4b4e7ae67c14633c7c852ce6ef2980114c228e5e6e1ccdd130
|
|
BLAKE2b-256 checksum How to use checksums |
0796eb349c04d34221d31fe1377cc582e6163015662abbebd4695e751418afe4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 30, 2026.
Transparency logRelease files / agentic_api-0.9.0-py3-none-macosx_11_0_arm64.whl
| Download URL | agentic_api-0.9.0-py3-none-macosx_11_0_arm64.whl |
|---|---|
| Size | 20.1 MB |
| Tags | Python 3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
8e8f9ea16c0b2be918f5e35679e6409e6a88647675c608ea8ffb0f7c179f9f20
|
|
BLAKE2b-256 checksum How to use checksums |
622786b7a78d09db6afc756818c6903a74a0e2afa9c0e74d829733a773f14e3e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 30, 2026.
Transparency logRelease files / agentic_api-0.9.0-py3-none-macosx_10_12_x86_64.whl
| Download URL | agentic_api-0.9.0-py3-none-macosx_10_12_x86_64.whl |
|---|---|
| Size | 20.9 MB |
| Tags | Python 3 macOS 10.12+ x86-64 |
|
SHA-256 checksum How to use checksums |
4c1eed39f01cd6e235c9f4da3bd8f58cd9414b2ff49d474e84b9c87a12595f10
|
|
BLAKE2b-256 checksum How to use checksums |
4d5c7c473e9b4dd9a0164efba08a9ce1da8ee84d4a6925537d5189783f6cb253
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 30, 2026.
Transparency log
