v1.0.0

[v1.0.0] - 2026-09-05

Breaking Changes

• Renamed to MagiCore: Renamed the Mem0Sharp package, assembly, root namespace, solution, projects, tests, evaluation harness, and repository paths to MagiCore. Consumers must replace the old package reference and update using Mem0Sharp directives to using MagiCore.

Added

• 3D Spatial Memory: Added provider-neutral APIs for storing timestamped 3D observations and recalling them by map, user or agent scope, Euclidean radius, observation time, confidence, and entity identity.
• Robotics Object Memory: Added event-time reconstruction of object beliefs from frame-aware sensor evidence, including visibility, freshness, uncertainty, conflict, relocation, conservative association, and spatial-relation states.
• Robot Action Episodes: Added persistence and recall for controller-reported action attempts with measured poses, outcomes, feedback, and spatial, temporal, action, and heading filters.
• Godot Robot Sample: Added a 3D warehouse robot sample using OpenAI vision and embeddings with PostgreSQL/pgvector persistence, plus offline and live memory checks.

Fixed

• VectorData Persistence Enumeration: Fixed VectorDataMemoryStore.GetAllAsync so a new store instance can enumerate persisted records with scope filtering.

Documentation

• Reworked the README and project artwork for the MagiCore identity, and documented spatial memory, robotics evidence, action-history boundaries, architecture, and Godot sample setup.

Full Changelog: v0.3.1...v1.0.0

v0.3.1

[v0.3.1] - 2026-09-02

Added

• Event-Time Retrieval: Added optional reference timestamps, explicit time ranges, and confidence-gated deterministic query interpretation without requiring persistence schema changes.
• Evaluation Harness: Expanded the evaluation suite with deterministic capability checks, a self-contained four-domain longitudinal dataset, configurable quality scenarios, event-time comparisons, dataset validation, and JSON/Markdown reporting.
• Multi-Agent Group Chat Sample: Added an Agent Framework sample with isolated per-agent long-term memories, personality-driven participants, temporal and point-in-time recall, strict isolated-memory testing, and private memory inspection.

Full Changelog: v0.3.0...v0.3.1

v0.3.0

[v0.3.0] - 2026-08-30

⚠️ Breaking Changes

• Single-Package Architecture with Microsoft.Extensions.VectorData Consolidation: Consolidated all storage and vector database operations directly into the core Mem0Sharp package. Removed legacy Mem0Sharp.PostgreSQL, Mem0Sharp.SQLite, and Mem0Sharp.VectorData satellite packages.
• Any MEVD connector (Microsoft.SemanticKernel.Connectors.*, CommunityToolkit.AI.VectorStore.*) can now be plugged directly into VectorDataMemoryStore (built into Mem0Sharp) to support PostgreSQL/pgvector, SQLite, Azure AI Search, Redis, Qdrant, Milvus, Pinecone, and more.

Added

• Point-in-Time Memory Reads: Added SearchAtAsync, GetAllAtAsync, and opt-in ITemporalMemoryStore support for non-destructive historical queries.
• Filtered Rollback: Corrected RollbackAsync filtering so recovery can be limited to matching users, metadata subjects, and other memory scopes while preserving complete snapshots and embeddings.

Improved

• Single Unified Package: Installing dotnet add package Mem0Sharp provides the full feature set without requiring additional provider packages.
• Updated samples/McpServer, samples/AgentFrameworkMemory, and evaluation/Mem0Sharp.Evaluation to use VectorDataMemoryStore.

Full Changelog: v0.2.2...v0.3.0

v0.2.2

[v0.2.2] - 2026-08-22

Added

• Multi-targeted the core, PostgreSQL, and SQLite packages for .NET Standard 2.0, .NET 8, .NET 9, and .NET 10.
• Added per-target test execution plus runtime smoke coverage for the .NET Standard 2.0 package assets.

Full Changelog: v0.2.1...v0.2.2

v0.2.1

[v0.2.1] - 2026-08-16

Added

• Admission Gate Defense Layer: Added NoveltyAdmissionGate, PromptInjectionAdmissionGate, and CompositeAdmissionGate to reject duplicate or malicious memory candidates before persistence.
• Trajectory Tracking: Extended MemoryService and the public contracts with trajectory persistence support, including AppendTrajectoryAsync, GetTrajectoriesAsync, and on-demand extraction from stored trajectories.
• History Rollback Support: Added rollback and history restoration APIs to in-memory and persistence-backed stores, including RollbackAsync and RollbackToHistoryAsync.

Improved

• Memory Lifecycle Safety: Hardened consolidation and stale-memory workflows by combining rollback/trajectory tracking with stricter admission filtering and verification paths.
• Test Coverage: Expanded unit tests for admission gates, consolidation behavior, and memory behavior scenarios to cover the new safeguards and lifecycle features.

Full Changelog: v0.2.0...v0.2.1

v0.2.0

[v0.2.0] - 2026-08-15

⚠️ Breaking Changes

• Storage Interface Consolidation: Merged 8 fragmented storage interfaces (IVectorMemoryStore, IBulkMemoryStore, IBatchMemoryStore, IAtomicMemoryStore, IBatchVectorMemoryStore, IMemoryHistoryStore, IResettableMemoryStore) into a single cohesive IMemoryStore.
• Embedding Generator Consolidation: Merged IBatchEmbeddingGenerator into IEmbeddingGenerator with default interface fallback.
• Memory Extractor Consolidation: Merged IBehaviorAwareMemoryExtractor into IMemoryExtractor with ExtractAsync(messages, options, ct).
• Canonical Service Signatures: Standardized IMemoryService and MemoryService around canonical options records (MemoryAddOptions, MemorySearchOptions, MemoryPageOptions, MemoryUpdate).

Added

• SIMD Hardware Acceleration: Integrated System.Numerics.Tensors across vector cosine similarity (TensorPrimitives.CosineSimilarity), vector normalization (TensorPrimitives.Norm), and vector scaling (TensorPrimitives.Divide).
• Native Qdrant REST Search: Implemented native REST vector search via POST collections/{name}/points/search and POST collections/{name}/points/search/batch with payload filter translation.
• SQLite SQL Pushdown: Pushed down user_id, agent_id, run_id, scope, behavior, memory_type, and expires_at filters directly into parameterized SQL WHERE clauses, streaming records via IAsyncEnumerable<Memory>.
• PostgreSQL Graph Store Query Pushdown: Term pattern matching for graph boost calculations pushed down to database index scans with ILIKE ANY($1) instead of full table scans.
• Concurrent LLM Reranking: Added bounded concurrent scoring with Parallel.ForEachAsync (MaxDegreeOfParallelism = 8) in LlmReranker.
• Reverse Index in In-Memory Entity Store: Added reverse lookup index (memoryId -> HashSet<string>) to achieve $O(1)$ memory deletions.
• Resilient JSON Parsing: Added markdown fence stripping (```json) and JSON array slice extractors in LlmMemoryExtractor and LlmGraphMemoryExtractor.
• Strongly-Typed API DTOs: Migrated OpenAiCompatibleClient, AnthropicClient, and OllamaClient from generic JsonNode heap allocations to strongly-typed DTO records and safe base URI combining.

Optimized

• BM25 Hybrid Search Complexity: Precomputed document frequencies reduced BM25 search complexity from $O(D^2 \cdot T)$ to $O(D \cdot T)$ with zero-allocation span tokenization.
• In-Memory Streaming: Removed unnecessary Task.Yield() state machine overhead in InMemoryStore.GetAllAsync.

Full Changelog: v0.1.7...v0.2.0

v0.1.7

v0.1.7

Mem0Sharp: Long-term memory lifecycle and evaluation upgrade

This release focuses on making Mem0Sharp behave more like a real long-term memory system instead of a simple fact store.

Highlights

• Added recency-aware retrieval and freshness-window tuning for time-sensitive memory recall.
• Added stale-memory forgetting and consolidation to model evolving preferences and outdated facts.
• Improved evaluation coverage with realistic long-horizon and retention scenarios.
• Strengthened behavior-aware memory support for normal, dreaming, random-thoughts, and personal-memory modes.
• Updated docs and published benchmark results to match the current verified run.

What’s new

• Long-term memory lifecycle:
  • recency bias during search
  • freshness filtering for newer vs. stale facts
  • forgetting of outdated or superseded memories
  • consolidation for preference drift and memory refinement
• More realistic benchmark scenarios:
  • realistic-long-haul
  • stale-forget
  • stricter threshold testing
  • richer multi-session behavioral memory evaluation
• Improved evaluation fidelity:
  • benchmark outputs now reflect real long-term memory behavior
  • self-test mode remains deterministic and safe for plumbing validation without provider credentials

Verified evaluation results

Fresh run results from the current benchmark matrix:

• realistic-long-haul: 91% accuracy, 100% retrieval hit rate
• stale-forget: 86% accuracy, 94% retrieval hit rate
• behavior-personal-memory: 100% accuracy, 94% retrieval hit rate
• llm-rerank: 100% accuracy, 100% retrieval hit rate

Why this matters

Mem0Sharp now better handles:

• changing user preferences over time
• stale or outdated memories
• long-running agent memory that must remain relevant across sessions
• behavior-specific memory patterns that feel more human and contextual

Full Changelog: v0.1.6...v0.1.7

v0.1.6

Mem0Sharp 0.1.6

Released: 2026-08-11

Highlights

• Split persistence providers into separate NuGet packages:
  • Mem0Sharp
  • Mem0Sharp.PostgreSQL
  • Mem0Sharp.SQLite
• Mem0Sharp core is now dependency-free.
• Added atomic memory/history persistence for built-in stores.
• Added memory provenance with behavior-aware retrieval.
• Factual search now excludes associative memories by default.
• Added fail-closed entity and graph enrichment.
• Updated OpenAI configuration defaults to gpt-5.6-luna.
• Kept embeddings on text-embedding-3-small, since Luna does not support embeddings.
• Added external evaluation dataset support and confidence intervals.
• Pinned SQLite runtime dependencies to patched versions.
• Release workflow now publishes all three packages with the same version.

Installation

dotnet add package Mem0Sharp --version 0.1.6
dotnet add package Mem0Sharp.PostgreSQL --version 0.1.6
dotnet add package Mem0Sharp.SQLite --version 0.1.6

Only install the provider package required by the application. Provider namespaces remain Mem0Sharp, so existing source code remains compatible after adding the provider reference.

Evaluation

The latest 10-scenario evaluation achieved:

• 96%: infer-off, dreaming, and personal-memory
• 92%: no-hybrid and conflict-resolution
• 88%: no-dedup
• 83%: baseline
• 75%: LLM reranking and strict threshold
• 58%: random thoughts

Detailed results are available in evaluation.md, with raw Markdown and JSON reports.

Full Changelog: v0.1.5...v0.1.6

v0.1.5

What's New?

Added

• Added configurable memory behaviors:
  • Normal
  • Dreaming
  • Random thoughts
  • Personal memory
• Added behavior-aware extraction through IBehaviorAwareMemoryExtractor.
• Added behavior and persona prompts for LLM-based memory extraction.
• Added MCP support for behavior and prompt options in add_memory.
• Added a runnable MemoryBehaviors sample.
• Added unit tests for memory behaviors and MCP integration.

Documentation

• Expanded the README and API documentation with memory behavior details.
• Added getting-started guidance and examples for behavior-shaped memories.
• Clarified Mem0Sharp’s native memory capabilities.

Full Changelog: v0.1.4...v0.1.5

v0.1.4

What's New?

Added

• Qdrant memory store with configurable options.
• Cohere, CrossEncoder, and ZeroEntropy reranker providers.
• Anthropic and Ollama model clients.
• New Getting Started, Ollama, and Postgres/OpenAI samples.
• YAML configuration for OpenAI integration tests.

Improved

• Expanded batch memory operations and history persistence.
• Enhanced PostgreSQL and OpenAI integration coverage.
• Added provider and reranker tests.
• Updated API, provider, persistence, parity, and onboarding documentation.
• Improved solution organization and sample discoverability.

Testing

• Added Qdrant and PostgreSQL history integration tests.
• Added coverage for model providers, rerankers, batch operations, and persisted history.

Full Changelog: v0.1.3...v0.1.4