A
licenseNot graded
qualityA
maintenanceProvides semantic memory and persistent storage for Claude, leveraging ChromaDB and sentence transformers for enhanced search and retrieval capabilities.
3
1,479 PyPI
2,090
Apache 2.0
AICortex
by IkarusMK
Related Servers
Alternatives to AICortex
- AlicenseAqualityAmaintenanceBasic Memory is a knowledge management system that allows you to build a persistent semantic graph from conversations with AI assistants. All knowledge is stored in standard Markdown files on your computer, giving you full control and ownership of your data. Integrates directly with Obsidan.md1219,662 PyPI4,496AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceBuild Real-Time Knowledge Graphs for AI Agents32,562Apache 2.0
Related Servers
- AlicenseNot gradedqualityBmaintenanceA self-hosted MCP server that provides any LLM with a graph-backed memory layer of your life—tasks, email, finance, contacts, calendar—plus autonomous agent offices that act on your behalf.3Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables self-hosted, persistent AI identity and long-term memory across clients, models, and agent surfaces, with multi-resident isolation, shared world knowledge, governed memory writes, correction and forgetting, keyword or optional semantic recall, and MCP or HTTP access.59MIT
- AlicenseNot gradedqualityBmaintenanceProvides a self-hosted shared memory service that lets AI agents capture and recall durable facts, decisions, and context across multiple tools and MCP-capable clients.3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server providing persistent brain storage for LLM agents, including memory, personality, social intelligence, and context management.1MIT
- AlicenseNot gradedqualityBmaintenanceProvides AI companion agents a local-first, append-first long-term memory backend with layered memory, hybrid recall, review-based updates, and a continuity sub-brain, exposed via REST and MCP interfaces.3MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to maintain persistent personal memory and portable skills across MCP-compliant clients, with hybrid semantic recall and deterministic SQL analytics.-
TDQS
A4.3/5.0
Scored across 11 tools
Disambiguation4/5
The search/read/load pairs are carefully differentiated: memory_search returns snippets then memory_read full text, skill_search finds names then skill_load loads SKILL.md, integration_search finds tools then integration_call runs them. The exception is bootstrap vs cortex_start, which are documented as functionally identical, giving an agent a genuine coin-flip on the first call. The remaining tools (memory_write, session_save, task_list) have clearly separate purposes.
Naming Consistency4/5
Nine of eleven tools follow a clean resource_verb snake_case pattern (memory_read, skill_load, integration_call, session_save, task_list). bootstrap is a bare noun and cortex_start inverts the word order (prefix + verb), but neither is cryptic and both are readable in context.
Tool Count5/5
Eleven tools is well within a healthy range for a personal-assistant/brain server spanning memory, skills, integrations, sessions and tasks. Each core tool earns its place by covering a distinct capability surface rather than duplicating another. Extra operations (task_add, task_claim, secret_set) are correctly pushed behind integration_call instead of bloating the direct surface.
Completeness4/5
Memory, skills and integrations each have a coherent find-then-act lifecycle, and write-replaces-title covers memory updates. Two minor asymmetries remain: there is no memory delete/forget tool, and session_save has no matching session_read (resume relies on cortex_start surfacing the last session). Task creation and claiming are reachable only indirectly via integration_call, which is workable but less discoverable than task_list being first-class.
Maintenance
ActivityMaintained
ResponsivenessSyncing