Becomer: LLM-agnostic persistent memory API. Store and recall memories across GPT, Claude, Gemini, or any model — zero tokens per recall.

by Becomer-net

197 downloads
Not rated
GitHub

About

BECOMER gives any LLM persistent memory across sessions — without spending a single token on retrieval.

Details

Author
Becomer-net
Downloads
197
Categories
AI

- LLM-agnostic persistent memory with zero token cost per recall
- Achieves 94.4% on the LongMemEval benchmark
- Multi-tenant isolation via user_id parameter
- Three integration modes: Python SDK, MCP, and REST API
- Zero dependencies – pure Python standard library only
- LangChain, OpenAI, Anthropic, and other framework examples provided

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Becomer: LLM-agnostic persistent memory API. Store and recall memories across GPT, Claude, Gemini, or any model — zero tokens per recall.
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install the Python package via pip install becomer, obtain a free API key from becomer.net, then instantiate a Client and call .store() / .recall() in your code. For MCP integration, add a JSON configuration to your MCP host pointing to python -m becomer with the environment variable BECOMER_API_KEY. No code changes are needed when using the MCP server.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "becomer: llm-agnostic persistent memory api. store and recall memories across gpt, claude, gemini, or any model \u2014 zero tokens per recall.": {
            "becomer": {
                "command": "python",
                "args": [
                    "-m",
                    "becomer"
                ],
                "env": {
                    "BECOMER_API_KEY": "your-key"
                }
            }
        }
    }
}

McpServers

{
    "becomer": {
        "command": "python",
        "args": [
            "-m",
            "becomer"
        ],
        "env": {
            "BECOMER_API_KEY": "your-key"
        }
    }
}

Recall

curl -X POST https://becomer.net/v1/recall \ -H "Authorization: Bearer bk-your-api-key" \ -H "Content-Type: application/json" \ -d '{"query": "user preferences", "top_k": 5}'

---

Multi-tenant (one key, many users)

Building a product where each of your users needs their own isolated memory? Pass user_id — no extra keys needed.

python
from becomer import Client

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.