Knowledge & Memory

Persistent memory for AI agents — pgvector + BM25 keyword search with RRF fusion, credential scrubbing, auto-consolidation.

MCP persistent memory service — let AI assistants remember across sessions. Powered by Qdrant vector search + official embeddings (via OpenAI-compatible relay or Gemini Vertex AI) with Ollama fallback and hybrid retrieval (vector + BM25).

AI Governance Era v6.1: loungeservice-grade project initialization. Creates 8-folder structure with complete AI governance (AI_RULES.md, AI_ROLE_MATRIX.yaml, NAMING_EXCEPTIONS.md, DEVELOPMENT.md, project.md) and bridge files (.cursorrules, .windsurfrules)

The only MCP that enforces tests before merge. Full-cycle development automation with testing gates, workflow orchestration, knowledge graph memory, and context health tracking.

Living off the Land binaries MCP server — GTFOBins, LOLBAS, LOOBins, LOLDrivers, LOLRMM, LOLESXi, LOTP, LOLC2, WADComs intelligence with attack graph reasoning, privilege escalation paths, defense evasion, detection engineering

Local-first persistent memory and session continuity MCP server for AI agents

Persistent memory system for Claude Code. Zero API key. Zero Python. 7 hooks + MCP server + SQLite FTS5 + semantic search + knowledge graph + two-way Obsidian vault.

Local-first persistent memory MCP server with PARA + Zettelkasten + SQLite FTS5

Org-wide persisted memory for AI coding agents via AWS Bedrock AgentCore. MCP server with short-term session events, long-term semantic search, and user/project/org namespaces.

Persistent memory for visual intelligence. MCP server for the Phototology registry: analyze photos with composable lenses, enrich files with EXIF/IPTC/XMP metadata, and look up cached results for free. Works with local files. Analyze once. Remember foreve

Mnemosyne MCP: FREE Local Embeddings for Knowledge Graph Memory - No API Keys Required

Local-first codebase knowledge-graph MCP server. Parses your repo into a symbol graph and serves it to AI coding agents so they stop wasting tokens re-scanning files. Watch-first: the graph stays fresh as you type.

Monitor any AI agent system. Auto-detects failures, sends alerts, audits OS processes. Zero config, zero dependencies.

Claude Code that gets sharper every session: the persistent-memory and runtime-discipline layer built on the 7 Laws of AI Agent Discipline. It grounds every edit in real facts before it lands and, through the Mulahazah engine, turns each fix into a reusab

Statically extracts a TypeScript project's dependency graph (imports, calls, NestJS DI wiring) into a queryable SQLite database, plus an MCP server so an LLM can navigate it.

Model Context Protocol server for Astrivya Knowledge Graph — 18 tools for AI coding agents to read/write/query the AKG

MCP server for memory management with long-term and short-term memory capabilities using local database

Open Targets MCP — disease/target/drug knowledge graph.

CLI tool for structured software specifications. Validate .dog files, compile .dag graphs, query via MCP.

SafeClaw Neurosymbolic Governance plugin for OpenClaw — validates AI agent actions against OWL ontologies and SHACL constraints