[KongchangAI]
Concept持久本地记忆层

PLML

A user-controlled memory architecture proposal for AI assistants that addresses unreliable cross-session memory by storing conversation history locally, retrieving relevant fragments locally and sharing only necessary context with the model.

Timeline (last 90 days)

Oct 19

Bert Singels is a 54-year-old autistic Dutch man who, based on his own frustrating experience using AI assistants, proposed the PLML (Persistent Local Memory Layer) technical proposal.

Unverified50%
Oct 19

The core principles of PLML are local storage, local retrieval, sharing only what is necessary, and decoupling the three functions of long-term storage, context retrieval, and language model inference.

Unverified50%
Oct 19

The PLML proposal points out that the problem is not whether conversation data is stored, but whether the right information can be retrieved and supplied to the model at the right moment.

Unverified50%
Oct 19

PLML uses SQLite or a similar local database to store conversation messages and their metadata, and uses full-text indexes and optional vector indexes to support retrieval.

Unverified50%
Oct 19

PLML's local retrieval engine combines multiple methods such as full-text search, semantic search, metadata filtering, recency and relevance ranking, and source message retrieval.

Unverified50%
Oct 19

The PLML design supports two integration modes simultaneously: Mode A (a browser extension interacting with existing chat interfaces) and Mode B (sending context directly via API or application integration), and does not bind the archive to either mode.

Unverified50%
Oct 19

In scenarios where accuracy is critical, the context manager should prefer original source material; summaries can speed up retrieval but should not become the sole record of important technical details.

Unverified50%
Oct 19

A key security stance of the PLML architecture is that archived messages should be treated as historical information rather than automatically trusted instructions; the local agent must not allow retrieved content to override current user intent or security controls.

Unverified50%
Oct 19

The PLML proposal estimates that assuming a user exchanges about 24,000 words per day, at 6 bytes per word, a year of raw text is about 52MB; planning at 200MB per user per year gives 200TB for 1 million users and 180PB for 900 million users.

Unverified50%
Oct 19

The PLML proposal advocates that local archives use open, documented data formats, so that users can switch between AI providers without having to rebuild their personal history or depend on proprietary memory formats.

Unverified50%

1 more timeline events

All Facts (11)

Unverified

Bert Singels is a 54-year-old autistic Dutch man who, based on his own frustrating experience using AI assistants, proposed the PLML (Persistent Local Memory Layer) technical proposal.

50%
Unverified

The core principles of PLML are local storage, local retrieval, sharing only what is necessary, and decoupling the three functions of long-term storage, context retrieval, and language model inference.

50%
Unverified

The PLML proposal points out that the problem is not whether conversation data is stored, but whether the right information can be retrieved and supplied to the model at the right moment.

50%
Unverified

PLML uses SQLite or a similar local database to store conversation messages and their metadata, and uses full-text indexes and optional vector indexes to support retrieval.

50%
Unverified

PLML's local retrieval engine combines multiple methods such as full-text search, semantic search, metadata filtering, recency and relevance ranking, and source message retrieval.

50%
Unverified

The PLML design supports two integration modes simultaneously: Mode A (a browser extension interacting with existing chat interfaces) and Mode B (sending context directly via API or application integration), and does not bind the archive to either mode.

50%
Unverified

In scenarios where accuracy is critical, the context manager should prefer original source material; summaries can speed up retrieval but should not become the sole record of important technical details.

50%
Unverified

A key security stance of the PLML architecture is that archived messages should be treated as historical information rather than automatically trusted instructions; the local agent must not allow retrieved content to override current user intent or security controls.

50%
Unverified

The PLML proposal estimates that assuming a user exchanges about 24,000 words per day, at 6 bytes per word, a year of raw text is about 52MB; planning at 200MB per user per year gives 200TB for 1 million users and 180PB for 900 million users.

50%
Unverified

The PLML proposal advocates that local archives use open, documented data formats, so that users can switch between AI providers without having to rebuild their personal history or depend on proprietary memory formats.

50%
Unverified

PLML's development roadmap is divided into six incremental phases: local archive, automatic capture, context retrieval, browser automation, multi-provider support, and reliability and security.

50%

Source Articles