How to use Octop Memory: what you can do with it

4 use cases

• Keep an assistant's preferences across sessions locally

  Store user preferences in a local SQLite file and recall them in later sessions.

  • REPO TencentCloud/octop-memory
  • Personal productivity
  • Intermediate
  View prompt

  Use the octop-memory repo to store the preference <preference text> in a local SQLite file at ./demo.sqlite under namespace demo. Then recall it with the query <query term> and return the rendered result. Verify that the returned text contains the stored preference.

  Share Email me this

• Move accumulated agent memory to another host

  Pack memory from one supported host into a portable package and adopt it on another.

  • REPO TencentCloud/octop-memory
  • Personal productivity
  • Advanced
  View prompt

  Use the octop-memory repo to list memory sources, pack the memory of <source host> into a .hmpkg file at <output path>, and adopt it on <target host>. Report the output of the portable doctor check and confirm that the package is not added to source control.

  Share Email me this

• Add capture and recall to a custom Python agent

  Call MemoryService from your own agent loop to capture turns and recall context.

  • REPO TencentCloud/octop-memory
  • Personal productivity
  • Intermediate
  View prompt

  Use the octop-memory repo to wire MemoryService into the agent in <project path> with the SQLite database at <db path>. Run one captured turn and one recall with the query <query>, then return result.rendered. Verify that the recall output includes the text from the captured turn.

  Share Email me this

• Expose memory to agents in other languages over JSON-RPC

  Run the stdio bridge so a non-Python agent can read and write the same memory.

  • REPO TencentCloud/octop-memory
  • Personal productivity
  • Advanced
  View prompt

  Use the octop-memory repo to start the octopmemory-bridge process for the host <host name> and send one capture and one recall request for the query <query>. Return the recall response. Verify that the captured text appears in the recall response.

  Share Email me this

Quick start with Octop Memory

1. Check you have what it needs: Python 3.12 or newer; pip to install the octop-memory package; A database path for local SQLite storage, or a PostgreSQL DSN for server deployments.
2. Open TencentCloud/octop-memory on GitHub and read the README and license.
3. Run pip install octop-memory
4. Run pip install "octop-memory[cli]" to add the command line tool
5. Create a Memory object with namespace="demo" and backend_config={"db_path": "./demo.sqlite"}, then call memory.store("User prefers Python for backend services", topic="preferences")
6. Run octop-memory --db ./demo.sqlite --namespace demo recall "Python" to confirm the stored preference is found

These steps come from our top use case, Keep an assistant's preferences across sessions locally, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for TencentCloud/octop-memory

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

Octop Memory alternatives · Best AI repos for Personal productivity

About this repo

• Who it is forPython developers building or configuring a personal assistant or custom agent who need preferences and project context to survive across sessions.
• Why it is hot77 stars, launched 30 days ago, picked up by one AI source we track
• LanguagePython
• Sourcegithub.com/TencentCloud/octop-memory · Back to Hot repos

Requirements

• Python 3.12 or newer
• pip to install the octop-memory package
• A database path for local SQLite storage, or a PostgreSQL DSN for server deployments
• An injected LLMClient only if you want automated extraction, promotion, or page regeneration; manual storage and lexical recall work without a model

Related repos

• Trended earlier REPO nixfred/infomarchy Infomarchy Infomarchy is an Omarchy desktop plugin that draws live AI agent sessions, usage, rate limits and machine stats onto the wallpaper in your current theme.
• Trended earlier REPO pengyue-polaron/deepseek-harness-genui DeepSeek Harness Genui A DeepSeek Harness plugin that lets an Agent build task-specific React + TypeScript apps whose saved selections carry into the next Agent turn.
• Trended earlier REPO Verlintas/BetterAIChat Better AI Chat BetterAIChat is a native Android AI assistant app that uses your own OpenAI, Anthropic, or Gemini API keys and can operate the phone through function calling.