Skip to main content

Pygent 0.3

Pygent is a PyTorch-like framework for composing LLM agents with no hidden per-call state from reusable Module graphs. Version 0.3 provides a single Execution owner for direct and managed calls, an asyncio Runtime, observable model/tool events, OpenAI-compatible adapters, portable tools and MCP adapters, ReAct, SQLite recovery, and HTTP/SSE workers.

Resource benchmark

Pygent 0.3.10 had the highest composite score among qualifying durable-runtime configurations at both tested loads. It recorded the lowest run time, P95, process-tree CPU, and peak RSS in each table.

Concurrent requests Durable rank Run P95 CPU Peak RSS Disk writes
200 1 of 4 3.828 s 3.758 s 4.906 s 102.2 MB 95.958 MB
1,000 1 of 3 23.070 s 22.603 s 23.453 s 211.1 MB 718.838 MB

This is not an all-metrics win: Pygent wrote 95.958 MB and 718.838 MB, respectively—74.2% and 156.8% more than LangGraph. The benchmark measures framework overhead on Windows with a local OpenAI-compatible mock, not model quality or production capacity, and the durable semantics are not identical. See the full methodology, tables, qualification rules, limitations, and optimization targets.

First principles

Pygent 0.3 第一原则 is the repository's highest authority. Module-specific first principles, SDK contracts, tests, examples, and code derive from it.

Quickstart

from pygent import AIMessage, Context, RecurrentModule, UserMessage


class Echo(RecurrentModule):
    async def forward(self, message, context):
        output = AIMessage(content=message.content.upper())
        return output, context + message + output


message, context = await Echo().invoke(UserMessage(content="hello"), Context())

Direct invoke(), stream(), and start() need no Runtime. Bind a Module to LocalRuntime when its call contract is supported and the application needs bounded concurrency, cancellation, deadlines, remote placement, durable history, or advanced Execution control. This standard recurrent example returns (message, context); ordinary Module inputs and results are user-defined. See the Execution contract.

Documentation

Development

uv sync --all-extras
uv run pytest -q
uv run ruff check src tests examples benchmarks
uv run mypy src benchmarks
uv build
python -m examples.service.main
uv run --extra performance python -m benchmarks run synthetic-smoke

Python 3.11+ is required. Apache-2.0; see LICENSE.

Metadata

Release files for pygent-ai 0.3.17

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pygent-ai 0.3.17
File Size Uploaded
pygent_ai-0.3.17.tar.gz 881.7 kB Details

Built distributions (wheels)

Table of built distributions (wheels) for pygent-ai 0.3.17
File
pygent_ai-0.3.17-cp311-abi3-win_amd64.whl CPython 3.11 abi3 Windows x86-64 Details
pygent_ai-0.3.17-cp311-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl CPython 3.11 abi3 Linux glibc 2.17+ x86-64 Details
pygent_ai-0.3.17-cp311-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl CPython 3.11 abi3 Linux glibc 2.17+ ARM64 Details
pygent_ai-0.3.17-cp311-abi3-macosx_11_0_arm64.whl CPython 3.11 abi3 macOS 11.0+ ARM64 Details
pygent_ai-0.3.17-cp311-abi3-macosx_10_12_x86_64.whl CPython 3.11 abi3 macOS 10.12+ x86-64 Details

Total release size: 13.6 MB

Release files / pygent_ai-0.3.17.tar.gz

Download URL pygent_ai-0.3.17.tar.gz
Size 881.7 kB
Tags Source
SHA-256 checksum
How to use checksums
d6ea77ae6fc77d23037538d5f2711507e993a122fbcef2ada469a6cc64bcf678
BLAKE2b-256 checksum
How to use checksums
4e42a546495e59e475f044daafa0bfc0d5c27fc250969723c77230a32dad1e2b
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 17, 2026.

Transparency log

Release files / pygent_ai-0.3.17-cp311-abi3-win_amd64.whl

Download URL pygent_ai-0.3.17-cp311-abi3-win_amd64.whl
Size 2.3 MB
Tags CPython 3.11 Windows x86-64 abi3
SHA-256 checksum
How to use checksums
511a5e3c4f24100c4734894e75295cc191d468ff45f9bb54ea9ed3787ea53fc5
BLAKE2b-256 checksum
How to use checksums
177261e150f0d60b60a0800860145a98bfb7c2aba0a46a8c411a11288db86ee2
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 17, 2026.

Transparency log

Release files / pygent_ai-0.3.17-cp311-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL pygent_ai-0.3.17-cp311-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size 2.7 MB
Tags CPython 3.11 Linux glibc 2.17+ x86-64 abi3
SHA-256 checksum
How to use checksums
df1a49271ca068b167d8e5f856ed71919a6771276e945c8e0f106f0b60af30ca
BLAKE2b-256 checksum
How to use checksums
e190a59a920e81d3e341d2337ee87c83dc5318f9df2b85264286fabca63f1a45
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 17, 2026.

Transparency log

Release files / pygent_ai-0.3.17-cp311-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

Download URL pygent_ai-0.3.17-cp311-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Size 2.7 MB
Tags CPython 3.11 Linux glibc 2.17+ ARM64 abi3
SHA-256 checksum
How to use checksums
8bc4b3e626ecb3c7b70c2721e31344fdab9124204dbe5cd37227dd9ab17ab733
BLAKE2b-256 checksum
How to use checksums
6726d56c9bb4c1f951f80c697f1d362418b1f6005a8ca2c2b1fd4dda056e959c
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 17, 2026.

Transparency log

Release files / pygent_ai-0.3.17-cp311-abi3-macosx_11_0_arm64.whl

Download URL pygent_ai-0.3.17-cp311-abi3-macosx_11_0_arm64.whl
Size 2.4 MB
Tags CPython 3.11 abi3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
53a30e92eea4d0caaac4afb9654423f8e8a6c2c3328120426b9d8911980c3709
BLAKE2b-256 checksum
How to use checksums
63927a4797de1c8655bbdcb7398c632c825c810876ecbde11cb4447193656828
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 17, 2026.

Transparency log

Release files / pygent_ai-0.3.17-cp311-abi3-macosx_10_12_x86_64.whl

Download URL pygent_ai-0.3.17-cp311-abi3-macosx_10_12_x86_64.whl
Size 2.5 MB
Tags CPython 3.11 abi3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
40a6c582409346f879cd78dc92e5fa4c5ec2af6819c514cb5880e43deb017c2e
BLAKE2b-256 checksum
How to use checksums
9b66f9019a920e34ddcc749842ff4cdd23587c39b5906177b9ffb712713b5851
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 17, 2026.

Transparency log

Release history Release notifications | RSS feed

0.3.26

6 release files

0.3.25

6 release files

0.3.24

6 release files

0.3.23

6 release files

0.3.22

6 release files

0.3.21

6 release files

0.3.20

6 release files

0.3.19

6 release files

0.3.18

6 release files

This release

0.3.17 This release

6 release files

0.3.16

6 release files

0.3.15

6 release files

0.3.14

6 release files

0.3.13

6 release files

0.3.12

6 release files

0.3.11

6 release files

0.3.9

6 release files

0.3.8

6 release files

0.3.7

6 release files

0.3.6

6 release files

0.3.5

6 release files

0.3.4

6 release files

0.3.3

6 release files

0.3.2

6 release files

0.3.1

6 release files

0.3.0

6 release files

0.2.21

6 release files

0.2.20

6 release files

0.2.19

6 release files

0.2.18

6 release files

0.2.17

6 release files

0.2.16

6 release files

0.2.15

6 release files

0.2.14

6 release files

0.2.13

6 release files

0.2.12

6 release files

0.2.11

6 release files

0.2.10

2 release files

0.2.9

2 release files

0.2.8

2 release files

0.2.7

2 release files

0.2.6

2 release files

0.2.5

2 release files

0.2.4

2 release files

0.2.3

2 release files

0.2.2

2 release files

0.2.1

2 release files

0.2.0

2 release files

0.1.15

2 release files

0.1.14

2 release files

0.1.11

2 release files

0.1.10

2 release files

0.1.9

2 release files

0.1.8

2 release files

0.1.7

2 release files

0.1.6

2 release files

0.1.5

2 release files

0.1.4

2 release files

0.1.3

2 release files

0.1.2

2 release files

0.1.1

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page