Skip to content

Add dakera-py to AI and Agents > Data Layer#3126

Closed
ferhimedamine wants to merge 2 commits into
vinta:masterfrom
ferhimedamine:add-dakera-py
Closed

Add dakera-py to AI and Agents > Data Layer#3126
ferhimedamine wants to merge 2 commits into
vinta:masterfrom
ferhimedamine:add-dakera-py

Conversation

@ferhimedamine
Copy link
Copy Markdown

dakera-py

dakera-py is the official Python SDK for the Dakera self-hosted agent memory server.

Why it fits the Data Layer subsection under AI and Agents:

  • Sits alongside mem0 as a production-grade agent memory solution, but with a self-hosted, privacy-first approach
  • Async-first API for store/recall, session management, decay configuration, and namespace operations
  • Designed for Python agent frameworks (LangChain, crewAI, autogen) that need persistent cross-session memory
  • Connects to a self-hosted Dakera server that scores 87.8% on the LoCoMo long-term conversational memory benchmark

The Data Layer subsection is exactly the right place — dakera-py gives Python agents the persistent memory layer they need alongside vector DBs and llama-index.

'd' sorts before 'i' (instructor) — entry was incorrectly placed
between llama-index and mem0.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@JinyangWang27
Copy link
Copy Markdown
Collaborator

@ferhimedamine Thanks for your submission. However, this project does not meet our acceptance criteria:

Repository age: The repository was created 2 months ago. We require a minimum of 3 months (or 6 months for Hidden Gem submissions) to ensure project stability.

GitHub stars: 0 star (minimum 100 required, or strong justification for Hidden Gem).

Please see our CONTRIBUTING.md for full requirements. You're welcome to resubmit once the project has matured and gained community traction.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants