DEDUPED Hot AI repos, turned into use cases Get the Monday 5
202 stars · Python

How to use Soda Mem: what you can do with it

What is Soda Mem? SodaMem is a Python memory layer for AI agents that stores facts with links back to their source turns and recalls them without LLM calls.

How do I use it? Run pip install "sodamem[chroma,llm]" to install Soda Mem; then run sodamem daemon ensure once to start the process that owns the stores; run sodamem install claude-code to wire the client to the daemon. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Give Claude Code memory that persists across sessions

    Install Soda Mem as a daemon and wire Claude Code to recall and retain context through MCP and hooks.

    View prompt
    Using the SodaMem repo at <repo path>, install SodaMem, start the daemon, and wire Claude Code to it. Expected output: the install command finishes without errors. Verify by starting a new Claude Code session and checking that a fact from a previous session is recalled.

  • Build a chatbot that updates facts when users change them

    Ingest a user message and recall the latest version of a fact, with the older version kept readable.

    View prompt
    In the SodaMem repo at <repo path>, write a Python script that ingests a message for user u1 saying the user moved to a new city, then calls build_context for where the user lives. Expected output: the new city in block.text with citations. Verify that the old city does not appear as the current answer.

  • Trace each recalled memory back to the turn it came from

    Check where a stored fact came from before trusting an agent's answer about a user.

    View prompt
    Using the SodaMem repo at <repo path>, run build_context for user <user_id> with the question <question>. Expected output: a list of citations, each tied to a session and turn. Verify that every line in the context has a citation.

  • Call Soda Mem memory from a TypeScript app over HTTP

    Use the sodamem npm client to fetch a zero-LLM context block from a running Soda Mem service.

    View prompt
    In the app at <project path>, install the sodamem npm package and call the SodaMem context endpoint for user <user_id>. Expected output: a context block returned with a text field. Verify the request succeeds with the API key sent as a Bearer token.

Quick start with Soda Mem

  1. Check you have what it needs: Python environment with pip available; An LLM provider API key set as SODAMEM_LLM_API_KEY, needed only for ingest; Docker or a running daemon is not required for the Python path, but coding tools need `sodamem daemon ensure` first.
  2. Open SodaMem/SodaMem on GitHub and read the README and license.
  3. Run pip install "sodamem[chroma,llm]" to install Soda Mem.
  4. Run sodamem daemon ensure once to start the process that owns the stores.
  5. Run sodamem install claude-code to wire the client to the daemon.
  6. Start a Claude Code session and confirm a stored fact from an earlier session is recalled.

These steps come from our top use case, Give Claude Code memory that persists across sessions, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for SodaMem/SodaMem

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Soda Mem alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers building AI agents or coding assistants who need memory that updates when facts change and can be traced to its source.
  • Why it is hot202 stars, launched 80 days ago
  • LanguagePython
  • Sourcegithub.com/SodaMem/SodaMem · Back to Hot repos

Requirements

  • Python environment with pip available
  • An LLM provider API key set as SODAMEM_LLM_API_KEY, needed only for ingest
  • Docker or a running daemon is not required for the Python path, but coding tools need `sodamem daemon ensure` first

Add this badge to your README

Maintain Soda Mem? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/SodaMem/SodaMem.svg)](https://dedupedai.com/use-cases/sodamem-sodamem/?utm_source=github&utm_medium=badge&utm_campaign=SodaMem-SodaMem)

HTML 

<a href="https://dedupedai.com/use-cases/sodamem-sodamem/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=SodaMem-SodaMem"><img src="https://dedupedai.com/badge/SodaMem/SodaMem.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Soda Mem

What is Soda Mem?

SodaMem is a Python memory layer for AI agents that stores facts with links back to their source turns and recalls them without LLM calls. It is an open-source project on GitHub: https://github.com/SodaMem/SodaMem.

How do I use Soda Mem?

Run pip install "sodamem[chroma,llm]" to install Soda Mem; then run sodamem daemon ensure once to start the process that owns the stores; run sodamem install claude-code to wire the client to the daemon. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Soda Mem for?

Developers building AI agents or coding assistants who need memory that updates when facts change and can be traced to its source.

What can I do with Soda Mem?

4 use cases so far, for example: Give Claude Code memory that persists across sessions; Build a chatbot that updates facts when users change them; Trace each recalled memory back to the turn it came from. Each has steps and a copy-paste agent prompt.

What do I need to run Soda Mem?

Python environment with pip available; An LLM provider API key set as SODAMEM_LLM_API_KEY, needed only for ingest; Docker or a running daemon is not required for the Python path, but coding tools need `sodamem daemon ensure` first.

What are alternatives to Soda Mem?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Soda Mem safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.