Python SDK for AGNT5 Platform - Build durable, resilient agent-first applications
Project description
AGNT5 Python SDK
Python SDK for building durable, resilient agent-first applications with the AGNT5 platform.
Features
- High-level AI components (Agents, Tools, Workflows)
- Durable execution with automatic failure recovery
- Memory systems (working, episodic, semantic, procedural)
- Multi-provider LLM support (Anthropic, OpenAI, Google, etc.)
- Rust-powered core for optimal performance
Installation
pip install agnt5
Quick Start
from agnt5 import Agent, tool
@tool
def search_web(query: str) -> str:
# Your search implementation
return f"Results for: {query}"
agent = Agent(
name="assistant",
instructions="You are a helpful AI assistant",
tools=[search_web],
memory=True
)
response = await agent.run("Search for Python tutorials")
Documentation
See the full documentation at docs.agnt5.dev
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
agnt5-0.1.0.tar.gz
(544.3 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agnt5-0.1.0.tar.gz.
File metadata
- Download URL: agnt5-0.1.0.tar.gz
- Upload date:
- Size: 544.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: maturin/1.8.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
73880be76bc6e643e84a4e69d7020146f94a92c8ce6c5cd05d7ab76f920086dd
|
|
| MD5 |
c9fa862eddc6189473c3e58fc6f3244f
|
|
| BLAKE2b-256 |
70c4cdcce70d63260053de9f276e8068d00b800937a792dbc4a65c985893346a
|
File details
Details for the file agnt5-0.1.0-cp39-abi3-macosx_11_0_arm64.whl.
File metadata
- Download URL: agnt5-0.1.0-cp39-abi3-macosx_11_0_arm64.whl
- Upload date:
- Size: 2.3 MB
- Tags: CPython 3.9+, macOS 11.0+ ARM64
- Uploaded using Trusted Publishing? No
- Uploaded via: maturin/1.8.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5a5790d6948c381dcb02386ff1b7fceac19ff40cd66f0e5c7b4ec28fec9c6587
|
|
| MD5 |
5aa0871ace8058f329d9ca5550ac5187
|
|
| BLAKE2b-256 |
4bf24dfff1162d1fad63073a94ca9eeaef7af9ccf002ca23d165596a0ed701b2
|