A portable knowledge-graph memory you pass in and get back. No database. 4 of 6 free.
Find what your knowledge base mentions but doesn't actually explain.
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
MCP server exposing NaN API tools: image generation/editing (flux-2-klein), TTS (kokoro), STT (whisper), embeddings and rerank
Graph-powered code intelligence for Claude Code. Semantic search + knowledge graph for better AI code understanding.
Temporal knowledge graph for codebases with constraint enforcement at the edit boundary.
Deterministic, namespace-isolated document retrieval with a CLI and MCP server.
Checkpoint and resume for AI agent runs, so crashed runs pick up where they left off.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.
Fetch URLs and return clean Markdown for RAG — nav, ads and boilerplate stripped.
Search the MITRE ATT&CK enterprise knowledge base for adversary techniques and tactics.
Local-first developer knowledge graph: watches project files, extracts entities and relationships with LLMs, and offers queries, a web dashboard and a CLI.
Create and manage vector database indexes, backups, and collections
Taiwan National Health Insurance (NHI) data: rejection codes, ICD-10 to procedure mappings, audit indicators and semantic search over NHI documentation.
Count keys in a JSON object. Values discarded.
Memory for AI agents: persistent L1/L2/L3, web-search savings, thread memory.
Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.
Cloudflare Workers AI inference: LLM chat completions (Llama, Qwen, DeepSeek), BGE text embeddings and Flux image generation.
Search and list latest international news (sources, comments, knowledge graph).
Web search via embedded SearXNG, content extraction and library docs indexing with hybrid FTS5 and semantic search using built-in Qwen3 embeddings.
The full Qdrant API as 58 MCP tools: plain-text semantic/BM25/hybrid search and a search advisor.
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Structural code context via TypeScript AST analysis: compressed symbol indexes, dependency graphs and git diffs, without a vector database or embeddings.
Cross-repository code knowledge graph for Java, Kotlin, JavaScript and TypeScript: call-flow tracing, taint analysis, reachability and license compliance.
Persistent memory for AI agents — history, context, semantic search, queues. 46 tools, stdio/SSE.
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 199 tools for Clau
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Pay-per-call APIs settled on Kaspa L1: text tools, web reading, embeddings and semantic search, Kaspa chain data, LLM inference and RISC Zero zk proving.
Local semantic code search with Git history. Works offline, no API key needed.
100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).
Windows AgentMemory downstream for Codex with project-scoped persistent memory, bounded cross-project recall, and an authenticated loopback MCP service; prebuilt Windows releases are available as an u
Local-first agent memory and knowledge base: hybrid dense and BM25 retrieval, document and webpage ingestion and optional RAG answers via local Ollama.
Local persistent memory for Claude Code: tracks mistakes and decisions via hooks, searches session history, detects loops and warns before edits.
Persistent memory shared across Claude Chat, Code and Cowork, stored in local SQLite with full-text search.
ไดเรกทอรีทั้งหมด
RAG กราฟ และหน่วยความจำระยะยาวของเอเจนต์ 2,590 เซิร์ฟเวอร์ เรียงจากที่ใช้มากที่สุด แต่ละรายการจะเปิดหน้าของผู้เผยแพร่