Skip to main content

Thread memory 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-0.1.9.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

threadmem-0.1.9-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

Details for the file threadmem-0.1.9.tar.gz.

File metadata

  • Download URL: threadmem-0.1.9.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-0.1.9.tar.gz
Algorithm Hash digest
SHA256 5bce237409b0d27d3bc9f85cb4f5fa8812b34a58a6ccf97b71daacc19bf65130
MD5 4d2ba0dc60e15365b546c6201ed09419
BLAKE2b-256 b8d71a9ded0398a6ef064d6bfc9cc8fceb52fcc9b57a063ea4782395d1aacf62

See more details on using hashes here.

File details

Details for the file threadmem-0.1.9-py3-none-any.whl.

File metadata

  • Download URL: threadmem-0.1.9-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-0.1.9-py3-none-any.whl
Algorithm Hash digest
SHA256 296a4d0f81cfbeb1d904999463ad449bcf411523585a8e3992008d1e4f1fe6ad
MD5 212f0dd97b88510348f429671fefa246
BLAKE2b-256 7d2082858075ff206ca3f1797a0897530566b4b946e7ffa1b377d0de5b3e7631

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