Skip to main content

Rich threads for AI agents

Project description


threadmem

Rich chat threads for AI agents
Explore the docs »

View Demo · Report Bug · Request Feature


Threadmem enables robust chat experiences with AI agents. It offers a Python backend for managing thread state as well as a React chat interface.

We support Agentscript for beautiful UI experiences.

Backend

Installation

pip install threadmem

Usage

Role Threads

Create a role based thread

from threadmem import Thread

thread = Thread()
thread.post("user", "Hello, Thread!")

# output in openai chat schema format
print(thread.to_oai())

Frontend

Installation

npm i @agentsea/threadmem

Develop

To test

make test

To publish

make publish

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

threadmem-0.1.6.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

threadmem-0.1.6-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

Details for the file threadmem-0.1.6.tar.gz.

File metadata

  • Download URL: threadmem-0.1.6.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.10.1 Darwin/22.6.0

File hashes

Hashes for threadmem-0.1.6.tar.gz
Algorithm Hash digest
SHA256 a6d8a44b2e8451449afb085824d6bbf34d3ed7f2e265773c4c81ae626884e33b
MD5 575ff146b5e5bdbd043c1970403ad024
BLAKE2b-256 7144fcae36dba38d993562b07bfa54bcf8f383ddad3c0ee6742df3de10aca127

See more details on using hashes here.

File details

Details for the file threadmem-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: threadmem-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 6.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.10.1 Darwin/22.6.0

File hashes

Hashes for threadmem-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 33652663f48d42723eda8cb6f2ae061da614c7c8c8af954004e5d08970025345
MD5 4b9ae268048125f89cd5b0eadcdfbb39
BLAKE2b-256 50cbf42ed5e7283061d0b8a8c8dd20cad4950b0ae2fe52c8e096cf6b2ca18fe3

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page