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

What is Becomer?

Becomer is a persistent memory API for AI applications. It lets you store and recall factual memories across any LLM (GPT, Claude, Gemini, etc.) using a proprietary retrieval engine. It is designed for developers who need long-term, zero-token recall in chatbots, assistants, or agentic workflows. Becomer is available as a Python SDK, an MCP server (for Claude Desktop, Cursor, etc.), and a REST API.

How to use Becomer?

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.

Key features of Becomer

• 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

Use cases of Becomer

• Give a chatbot memory across sessions without modifying the LLM provider
• Store user preferences (language, theme, dietary restrictions) for consistent behavior
• Build multi-user AI products where each user’s memory is fully isolated
• Replace context-window stuffing with a dedicated, high-accuracy memory layer

FAQ from Becomer

What makes Becomer different from a vector store?

Becomer uses a proprietary retrieval engine optimized for long-term conversational memory, outperforming the next-best solution by 3 points on the LongMemEval benchmark (94.4% vs 91.4%). It is designed specifically for storing and recalling factual statements about users, not for general document search.

What are the runtime dependencies?

Becomer is pure Python with zero external dependencies – only the standard library is required.

Where is my data stored?

All memories are stored on Becomer’s servers via API calls to becomer.net. The README does not specify self-hosting options.

What are the rate limits and pricing?

The free plan includes 1,000 API calls per month. The Pro plan offers 50,000 calls/month for ₹1,140/month (~$14). Multi-tenancy requires only one master key; billing counts against that key.

How do I authenticate and what transports are supported?

Authentication is via an API key (bk-your-api-key) passed to the client or set as an environment variable (BECOMER_API_KEY). Supported transports: Python SDK (direct), MCP (stdio via python -m becomer), and REST API (HTTP POST to becomer.net/v1/store and becomer.net/v1/recall).