feat(memory): #62-5 Semantic Memory Implementation #91

New Issue

cardosofelipe · 2026-01-05T00:16:26Z

cardosofelipe commented

2026-01-05 00:16:26 +00:00

Part of Issue #62 - Agent Memory System

Phase: 2 (Memory Types)
Priority: P1
Complexity: High

Overview

Implement semantic memory - fact storage with triple format (subject, predicate, object) and semantic search capabilities.

Components

backend/app/services/memory/semantic/memory.py - SemanticMemory class
backend/app/services/memory/semantic/extraction.py - Fact extraction from episodes
backend/app/services/memory/semantic/verification.py - Fact verification

Features

Fact storage with triple format (subject, predicate, object)
Confidence scoring and decay
Fact extraction from episodic memory
Conflict resolution for contradictory facts
Retrieval by query (semantic search)
Retrieval by entity (subject or object)
Source tracking (which episodes contributed)
Reinforcement on repeated learning

API

class SemanticMemory:
    async def store_fact(self, fact: FactCreate) -> Fact
    async def search_facts(self, query: str, limit: int = 10) -> list[Fact]
    async def get_by_entity(self, entity: str, limit: int = 20) -> list[Fact]
    async def reinforce_fact(self, fact_id: UUID) -> Fact
    async def deprecate_fact(self, fact_id: UUID, reason: str) -> None
    async def extract_facts_from_episode(self, episode: Episode) -> list[Fact]
    async def resolve_conflict(self, fact_ids: list[UUID]) -> Fact

Performance Target

Semantic memory search: <100ms P95

Acceptance Criteria

All features implemented
>90% test coverage
make validate-all passes
Multi-agent review completed

## Part of Issue #62 - Agent Memory System **Phase:** 2 (Memory Types) **Priority:** P1 **Complexity:** High ## Overview Implement semantic memory - fact storage with triple format (subject, predicate, object) and semantic search capabilities. ## Components - `backend/app/services/memory/semantic/memory.py` - SemanticMemory class - `backend/app/services/memory/semantic/extraction.py` - Fact extraction from episodes - `backend/app/services/memory/semantic/verification.py` - Fact verification ## Features - [ ] Fact storage with triple format (subject, predicate, object) - [ ] Confidence scoring and decay - [ ] Fact extraction from episodic memory - [ ] Conflict resolution for contradictory facts - [ ] Retrieval by query (semantic search) - [ ] Retrieval by entity (subject or object) - [ ] Source tracking (which episodes contributed) - [ ] Reinforcement on repeated learning ## API ```python class SemanticMemory: async def store_fact(self, fact: FactCreate) -> Fact async def search_facts(self, query: str, limit: int = 10) -> list[Fact] async def get_by_entity(self, entity: str, limit: int = 20) -> list[Fact] async def reinforce_fact(self, fact_id: UUID) -> Fact async def deprecate_fact(self, fact_id: UUID, reason: str) -> None async def extract_facts_from_episode(self, episode: Episode) -> list[Fact] async def resolve_conflict(self, fact_ids: list[UUID]) -> Fact ``` ## Performance Target - Semantic memory search: <100ms P95 ## Acceptance Criteria - [ ] All features implemented - [ ] >90% test coverage - [ ] `make validate-all` passes - [ ] Multi-agent review completed

cardosofelipe closed this issue

2026-01-05 03:26:49 +00:00

cardosofelipe referenced this issue

2026-01-05 10:04:59 +00:00

feat(mcp): Agent Memory System #62

cardosofelipe referenced this issue from a commit

2026-01-06 00:56:28 +00:00

feat(memory): #87 project setup & core architecture

cardosofelipe referenced this issue from a commit

2026-01-06 00:56:28 +00:00

feat(memory): add semantic memory implementation (Issue #91)

Sign in to join this conversation.