Memory Extraction

Mneno can extract structured memories from raw text. Deterministic extraction is the default and requires no provider.

Extract without storing

from mneno import MemoryClient

client = MemoryClient()
result = client.extract_memories(
    "The user is building Mneno. The user prefers Python 3.11."
)

for item in result.extracted:
    print(item.content, item.memory_type, item.importance)

print(result.errors)

The result reports its extraction mode, extracted memories, and validation errors.

Extract and add memories

result = client.add_from_text(
    "The user is building Mneno. The user prefers Python 3.11."
)

for item in result.extracted:
    print(item.memory_id, item.content)

Valid extracted memories can be added even when another extracted item fails validation.

Use an LLM provider

LLM-assisted extraction uses only the LLMProvider protocol. Provider output must be structured JSON and pass Pydantic validation.

from mneno import MemoryClient
from mneno.providers import DummyLLMProvider

client = MemoryClient(llm_provider=DummyLLMProvider())
result = client.extract_memories(
    "The user is building Mneno and prefers Python 3.11.",
    use_llm=True,
)

If use_llm=True and no provider is configured, Mneno raises a provider error. Invalid provider output produces explicit validation errors instead of being accepted silently.

LLM-assisted compaction wording

LLMs do not choose which memories are deleted, merged, or retained. Deterministic policy makes those decisions first. An LLMProvider may only improve wording for a merge group that deterministic compaction already selected.

diff = client.preview_compaction(use_llm=True)

If the provider returns invalid merge output, Mneno falls back to deterministic merged content.

Getting Started

Core Concepts

Advanced

Memory Extraction

Extract without storing

Extract and add memories

Use an LLM provider

LLM-assisted compaction wording

​Extract without storing

​Extract and add memories

​Use an LLM provider

​LLM-assisted compaction wording

Extract without storing

Extract and add memories

Use an LLM provider

LLM-assisted compaction wording