Sibyl-Labs/Sibyl-Memory — Durable, file-based long-term memory for AI agents.

Description and use

**Project Summary:**

Sibyl-Memory is an open-source, file-based long-term memory solution for AI agents, designed to enable repeatable agent workflows by coordinating multi-agent tasks, adding tool-use pipelines, and standardizing agent memory. This durable memory system is composed of five plugins, including an SDK, CLI, MCP server, Hermes adapter, and LangGraph BaseStore. With its high production readiness, Sibyl-Memory is suitable for serious pilots and has a strong ecosystem signal.

**Value Proposition:**
The primary value proposition of Sibyl-Memory lies in its ability to transform isolated prompts and tools into repeatable agent workflows. By providing a durable, file-based long-term memory solution, Sibyl-Memory enables AI agents to learn from past experiences, adapt to new situations, and perform complex tasks more efficiently.

**Practical Adoption Path:**
To adopt Sibyl-Memory, developers can start by evaluating its implementation signals, such as API/SDK/CLI, language metadata, or focused topics. Once familiar with the system, they can integrate Sibyl-Memory into their existing workflows by utilizing the SDK, CLI, or MCP server. The Hermes adapter and LangGraph BaseStore can be used to connect Sibyl-Memory to other tools and systems

Problem

Sibyl-Labs/Sibyl-Memory helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.

Source