ai-memory
An open-source AI programming memory-sharing tool written in Rust. It automatically records agent interactions via lifecycle hooks, using Markdown files stored in a Git repository as the memory substrate. The tool supports cross-tool and cross-device context sharing as well as structured task handoffs.
Core Facts
Timeline (last 90 days)
For teams, until the permission issue in Issue #708 is resolved, it is recommended to trial it internally on a small scale first, to avoid exposing sensitive projects to user groups with overly broad permissions.
Key improvements in ai-memory v3.1.1 include better session management and memory aging without needing to call the API.
ai-memory supports more than twenty agent tools for cross-agent relay.
When ai-memory launches an agent via the `ai-memory run` command, it preserves the full workflow and carries over the previous agent's local history projection.
ai-memory stores memories as editable markdown files.
The memory aging rate of ai-memory is configurable, helping teams manage the knowledge lifecycle.
ai-memory's Issue #708 points out that there is no project-based authorization mechanism in multi-user scenarios, and currently all authenticated users can access all projects.
ai-memory's tool calls and session boundaries are recorded automatically, without relying on explicit user commands.
ai-memory v3.1.1 was released on October 17.
The ai-memory project has been in existence for approximately four months and has reached 8,120 GitHub stars, growing at a rate of over a hundred stars per day.
6 more timeline events
All Facts (16)
Enterprise-grade multi-user AI agent memory management involves memory isolation between users, unified maintenance of shared organizational knowledge, and the implementation of role-based access control at the vector retrieval layer
65%UnverifiedFor teams, until the permission issue in Issue #708 is resolved, it is recommended to trial it internally on a small scale first, to avoid exposing sensitive projects to user groups with overly broad permissions.
50%UnverifiedKey improvements in ai-memory v3.1.1 include better session management and memory aging without needing to call the API.
50%Unverifiedai-memory supports more than twenty agent tools for cross-agent relay.
50%UnverifiedWhen ai-memory launches an agent via the `ai-memory run` command, it preserves the full workflow and carries over the previous agent's local history projection.
50%Unverifiedai-memory stores memories as editable markdown files.
50%UnverifiedThe memory aging rate of ai-memory is configurable, helping teams manage the knowledge lifecycle.
50%Unverifiedai-memory's Issue #708 points out that there is no project-based authorization mechanism in multi-user scenarios, and currently all authenticated users can access all projects.
50%Unverifiedai-memory's tool calls and session boundaries are recorded automatically, without relying on explicit user commands.
50%Unverifiedai-memory manages task handoffs through a protocol-based system where tasks carry types and ownership, and the claim operation is atomic to prevent two agents from competing for the same task.
50%UnverifiedThe recording, retrieval, and handoff functions under ai-memory's default path do not require an API Key, and retrieval relies on keyword and link matching without depending on large language models.
50%Unverifiedai-memory features a hierarchical forgetting mechanism where frequently used memories decay slowly and infrequently accessed notes are compressed into summaries, but the original records are preserved in the Git version chain and can be restored.
50%UnverifiedThe core memory store in ai-memory consists of Markdown files in a Git repository, with the database serving only as an index that can be rebuilt from the original files after deletion.
50%Unverifiedai-memory chooses keyword and link matching over semantic retrieval, sacrificing some semantic recall capability in exchange for offline availability, zero API costs, and portability compatible with the Git toolchain.
50%Unverifiedai-memory is an open-source project written in Rust for sharing memory across multiple AI coding assistants.
50%Unverifiedai-memory v3.1.1 was released on October 17.
50%