A
licenseA
qualityC
maintenanceEnables AI agents and MCP clients to store, retrieve, and manage bi-temporal, graph-aware facts in an embedded SQLite memory engine with token-budgeted recall and contradiction tracking.
6
1
MIT
ZenBrain
Officialby zensation-ai
Related Servers
Alternatives to ZenBrain
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenancePersistent long-term memory for MCP clients. Store and recall semantic facts, episodic events, and task state with vector-based relevance search. Write what matters, retrieve what's needed — memory that persists across sessions and agents, backed by a local SQLite store with optional embeddings for meaning-based lookup. Simple file-based storage, no external services required.MIT
- AlicenseNot gradedqualityDmaintenanceA local memory engine for AI agents. Stores conversation episodes, consolidates knowledge through a neuroscience-inspired lifecycle, and builds a personal knowledge graph — all in a local SQLite database.17MIT
- AlicenseNot gradedqualityCmaintenanceLocal-first persistent memory layer for AI agents. Provides hybrid search (FTS5 keyword + vector embeddings) over 223K+ knowledge chunks via MCP. Tools: brain_search, brain_store, brain_entity, brain_subscribe. Features pub/sub with stable agent identity, delivery tracking, and Claude --channels integration. SQLite + BrainBar Swift daemon on Unix socket.2,361 PyPI9Apache 2.0
- AlicenseNot gradedqualityCmaintenanceLocal-first semantic memory layer for MCP agents. Recall, remember, forget, stats over stdio. ChromaDB plus sentence-transformers, all on-machine.69 PyPIMIT
- AlicenseNot gradedqualityAmaintenanceProvides persistent, cooperative memory for LLMs via MCP, with SQLite storage and tools for capturing, recalling, consolidating, crystallizing, and forgetting memories across sessions.3MIT
TDQS
A4.6/5.0
Scored across 4 tools
Disambiguation5/5
Each tool has a clearly distinct role: recall reads, store writes, consolidate maintains, and health reports stats. Descriptions explicitly cross-reference to avoid confusion (e.g., 'to see how much is stored rather than what, use zenbrain_health'), and no overlap exists among the four operations.
Naming Consistency4/5
All tools share the zenbrain_ prefix and use snake_case, forming a predictable pattern. However, the action words mix verbs (recall, store, consolidate) with a noun (health), a minor deviation from a pure verb-based convention.
Tool Count5/5
Four tools cover the core memory lifecycle: write, read, maintain, and monitor. The count is well within the 3-15 well-scoped range, and each tool clearly earns its place without redundancy.
Completeness4/5
The surface covers storing, recalling, consolidating, and monitoring memory layers. Minor gaps exist: no explicit update or delete for non-core memories, though storing anew works around this and deletion is intentionally absent.
Maintenance
ActivityActive
ResponsivenessSlow