Persistent engineering knowledge base with source-backed wiki, agent-runtime and repository-context tools, contradiction and staleness checks, and PIN-gated private scopes and writes.
Semantic knowledge graph for Obsidian with graph, classification and hierarchy modes, local embeddings, semantic bridge discovery and drift detection.
Persistent fractal graph memory for coding agents: semantic search, hot/cold/archive context tiers and decision tracking on Qdrant.
Persistent memory with SQLite hybrid search (FTS5 and semantic), built-in Qwen3 embeddings and rclone sync across machines.
Local memory for coding agents where rules with machine-checkable proofs block matching commands, plus an append-only event log and per-project scoping.
Persistent semantic and graph-based agent memory in a single self-contained binary with embedded database and models.
Persistent memory for coding agents storing architecture decisions, bug root causes and conventions, with full-text search and token-budgeted context assembly.
SQLite-based memory with exponential decay: memories strengthen on access and fade when unused, limiting unbounded context growth.
Five-level AI collaboration system with persistent local-first memory via MemDocs and anticipatory capabilities.
Personal knowledge graph for Claude on Neo4j with typed entities, bi-temporal edges, weighted decay, contradiction detection and local embeddings.
YouTube knowledge base: summarize videos, fetch transcripts (even without captions), search channels and playlists, and save results for cross-session recall.
Hindsight: long-term memory for AI agents modeled on human memory.
Local-first memory for coding agents that turns coding sessions into reusable engineering memory: decisions, gotchas and domain knowledge.
Cybersecurity assessment of documents, questionnaires and reports: multi-format parsing, RAG knowledge base, risks, compliance gaps and remediations.
Persistent memory with swappable Postgres/pgvector, Qdrant or Neo4j backends, adaptive retrieval weighting, duplicate merging and stale-fact archiving.
Web search via embedded SearXNG, content extraction and library docs indexing with hybrid FTS5 and semantic search using built-in Qwen3 embeddings.
Reptile and exotic pet knowledge base: species identification, genetics calculator, care information, health diagnosis, prices and blockchain provenance.
MCP server for Kerabie: lets Claude, Cursor and other MCP clients work with your conversations, tickets, contacts, campaigns, knowledge base, analytics and AI tools
Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
MCP server providing Solidity smart contract security analysis tools, OWASP knowledge base, and development utilities for AI agents
Typed AI framework for TypeScript: provider routing and failover, durable agent graphs and workflows, retrieval over any vector store, MCP, evals, guardrails, and cost control
OmniQA: agentic test framework and product knowledge base. SDK, runner and CLI.
Universal LLM API client for 174 providers — chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.
ai-hub — work in your AI Hub Second Brain from the terminal, with the same verbs your AI agents use.
Real-time context window breakdown, prompt & thinking effort advisor, MCP server controller, and 5h/weekly quota telemetry sidecar for Google Antigravity.
Cursor plugin for HarnMem, the cross-harness agent memory: byte-stable first-prompt injection, five MCP memory tools, and session-end journaling. One shared store of plain, human-editable Markdown und
The essential MCP components for a project's context (AGENTS.md), cross-session memory, and identity — a base MCP on its own, or a drop-in extension for any existing MCP server. Discoverable through t
Cerefox — user-owned shared memory for AI agents. CLI + stdio MCP server + web UI + ingestion for a knowledge base on your own Supabase project (or fully self-hosted with Cerefox Local).
Give any agent self-improving memory you can trust in production. Every correction is kept, shown to your agent when it matters and enforced on Claude Code and Codex. Built-in memory security: notes c
AINative ZeroDB MCP Server - 93 operations for vector search, TurboQuant vector compression (PolarQuant + QJL), NoSQL, dedicated PostgreSQL management, files, events, RLHF, knowledge graph (entities,
Universal code development MCP server — search, analyze, navigate, review any codebase. 29 tools, semantic search, AST parsing, security scanning, dead code detection, complexity heatmaps, DB schema p
One semantic search across your sites, Drive, Notion, email, files and Basecamp.
A second brain your AI assistants share: your notes, chats and mail, and memories kept as Markdown.
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Semantic search and pattern discovery for Obsidian and markdown vaults.
Persistent scoped Qdrant memory for agents, through four explicit stdio MCP tools.
完整目錄
RAG、圖譜與代理長期記憶。共 2,674 個伺服器,最常用的排在前面。每個都會開啟發布者的頁面。