post-cortex
Active·★ 20·MIT·Updated 2026-10-20
Post-Cortex is an MCP server that provides AI assistants with persistent memory. It stores conversations, decisions, and insights in a searchable knowledge base with automatic entity extraction. All processing runs locally with no external API calls, ensuring privacy.
#ai#ai-memory#graph-rag#knowledge-graph#llm#lock-free#mcp#mcp-server
01
Features
01Persistent memory across sessions
02Semantic search with multilingual embedding
03Graph-RAG for enriched search results
04Knowledge graph with typed entities and relations
05Non-blocking writes with low latency
02
Compatibility
macOS
macOS (Homebrew)
Verified via docs
Linux
Linux (Homebrew)
Verified via docs
Cross-platform
All platforms (Cargo)
Verified via docs
03
Quick start
1
$ cargo install post-cortex-daemon --features "embeddings,surrealdb-storage"
04
Use cases
↳AI assistants with long-term memory across conversations
↳Knowledge management and retrieval for multi-session projects
↳Privacy-first local memory for AI tools
05
Alternatives
MemoryPilot★ 18
The most advanced AI memory server in the world. Hybrid search, Temporal Knowledge Graph, transformer embeddings, AAAK compression (3x token savings) — pure Rust, single binary, zero dependencies.
mcp-ts-core★ 153
TypeScript template for building Model Context Protocol (MCP) servers. Ships with declarative tools/resources, pluggable auth, multi-backend storage, OpenTelemetry observability, and first-class support for both local and edge (Cloudflare Workers) runtimes.
synaptic-memory★ 33
Brain-inspired knowledge graph: spreading activation, Hebbian learning, memory consolidation.
mcp-victoriametrics★ 239
The implementation of Model Context Protocol (MCP) server for VictoriaMetrics
jdocmunch-mcp★ 206
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
Comments
Log in to leave a comment
No comments yet. Be the first!