Skip to main content

Thread memory for AI agents

Project description


threadmem

Chat thread memory for AI agents
Explore the docs »

View Demo · Report Bug · Request Feature


ThreadMem is a simple tool that helps manage chat conversations with language models.

Installation

pip install threadmem

Usage

Role Threads

Role based threads are useful for managing openai-style chat schemas.

from threadmem import RoleThread

# Create a thread storing it in a local sqlite db
thread = RoleThread(owner_id="dolores@agentsea.ai")

# Post messages
thread.post("user", "Hello, Thread!")
thread.post("assistant", "How can I help?")
thread.post("user", "Whats this image?", images=["data:image/jpeg;base64,..."])

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

# Find a thread
threads = RoleThread.find(owner_id="dolores@agentsea.ai")

# Delete a thread
threads[0].delete()

Add images of any variety to the thread. We support base64, filepath, PIL, and URL:

from PIL import Image

img1 = Image.open("img1.png")

thread.post(
  role="user",
  msg="Whats this image?",
  images=["data:image/jpeg;base64,...", "./img1.png", img1, "https://shorturl.at/rVyAS"]
)

Integrations

Threadmem is integrated into:

  • MLLM - A prompt management, routing, and schema validation library for multimodal LLMs.
  • Taskara - A task management library for AI agents.
  • Skillpacks - A library to fine tune AI agents on tasks.
  • SurfKit - A platform for AI agents.

Community

Come join us on Discord.

Backends

Thread and prompt storage can be backed by:

  • Sqlite
  • Postgresql

Sqlite will be used by default. To use postgres simply configure the env vars:

DB_TYPE=postgres
DB_NAME=threads
DB_HOST=localhost
DB_USER=postgres
DB_PASS=abc123

Image storage by default will utilize the db, to configure bucket storage using GCS:

  • Create a bucket with fine grained permissions
  • Create a GCP service account JSON with permissions to write to the bucket
export THREAD_STORAGE_SA_JSON='{
  "type": "service_account",
  ...
}'
export THREAD_STORAGE_BUCKET=my-bucket

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-0.2.39.tar.gz (24.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

threadmem-0.2.39-py3-none-any.whl (27.8 kB view details)

Uploaded Python 3

File details

Details for the file threadmem-0.2.39.tar.gz.

File metadata

  • Download URL: threadmem-0.2.39.tar.gz
  • Upload date:
  • Size: 24.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.9 Darwin/23.4.0

File hashes

Hashes for threadmem-0.2.39.tar.gz
Algorithm Hash digest
SHA256 c6bb30c24e27456ce3498d330550cf3ab02b5c33e2a58747d86200213e659f17
MD5 cfba4b7eb2f7f491202e51655dd17228
BLAKE2b-256 f49801e1b6b4be23059578b6788093412b16994959f056221d3f86ae0737f9d0

See more details on using hashes here.

File details

Details for the file threadmem-0.2.39-py3-none-any.whl.

File metadata

  • Download URL: threadmem-0.2.39-py3-none-any.whl
  • Upload date:
  • Size: 27.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.9 Darwin/23.4.0

File hashes

Hashes for threadmem-0.2.39-py3-none-any.whl
Algorithm Hash digest
SHA256 8e51f16de07cc86499b1f50dae7aeee1f9faa90be82af991531b5c5c5f3ea64d
MD5 b32981f8f615c6e3e0da0fa479642797
BLAKE2b-256 b10e863cb2e1b447e08e6e6bf6c96aeff1d253785d1a88ca956d8a909153187e

See more details on using hashes here.

Supported by

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