Skip to main content

AmritaCore

Logo

PyPI Version Python Version License AmritaCore Discord QQ Group

AmritaCore is a lightweight Agent runtime built on top of AmritaSense. It delivers native async streaming, tool integration, event hooks, and memory management — everything you need to build interactive, production‑ready Agent applications without the overhead of heavyweight frameworks.

🚀 Fast Lookup

import asyncio
from amrita_core import create_agent


async def main():
    agent = create_agent(
        base_url="https://api.openai.com/v1",
        api_key="your-api-key",
        model="gpt-4o-mini",
    )
    chat = agent.get_chatobject("Hello, how are you?")
    print(await chat.full_response())


asyncio.run(main())

🔑 Key Features

  • Interactive‑first design — native async streaming with suspend/resume
  • Vendor‑agnostic adapter system — OpenAI, Anthropic, and extensible
  • Declarative dependency injection — type‑safe, based on function signatures
  • Event‑driven hooks — intercept and modify the processing pipeline
  • Tool system — @simple_tool, @on_tools, and MCP client support
  • Advanced memory management — automatic context window and token optimisation

📖 Documentation

Full guides, API references, and examples at core.amritabot.com.

🤝 Contributing

We welcome contributions! Please see our contribution guidelines for more information.

AIGC Content Licensing Policy

We use AACLP v1.0 for AIGC content licensing. See File for more details.

📄 License

This project is licensed under the Apache 2.0 License — see the LICENSE file for details. All versions of AmritaCore are released under Apache 2.0.

Other files

Metadata

Release files for amrita_core 1.4.0

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

Source distribution (sdist)

Source distribution for amrita_core 1.4.0
File Size Uploaded Provenance Actions
amrita_core-1.4.0.tar.gz 247.8 kB Without provenance Details for amrita_core-1.4.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for amrita_core 1.4.0
File Interpreter ABI Platform Actions
amrita_core-1.4.0-py3-none-any.whl Python 3 none any Details for amrita_core-1.4.0-py3-none-any.whl

Total release size: 438.2 kB

Release files / amrita_core-1.4.0.tar.gz

Download URL amrita_core-1.4.0.tar.gz
Size 247.8 kB
Tags Source
SHA-256 checksum
How to use checksums
b0331b24df878482c79b97c9297ad0e51d572a61e1e5c7182b96e385fb7131a6
BLAKE2b-256 checksum
How to use checksums
4f11a4be735c192cb825eb8a2eb110a671929d7193a458b994941cea601cbd5f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / amrita_core-1.4.0-py3-none-any.whl

Download URL amrita_core-1.4.0-py3-none-any.whl
Size 190.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
320a31dd954ca5c58555ba9badb3203aa5a5eba2ffbfec1a4abfabfd69a364f3
BLAKE2b-256 checksum
How to use checksums
7fe01bb8fa4f4ba5254d742da349d3a9b1e819047869b1f35c560ce8fe765c0f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for amrita_core 1.4.0

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.

Release history Release notifications | RSS feed

This release

1.4.0 This release

2 release files No provenance

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