Context window token analysis and budget management
YATS — Yet Another Token Saver. One-command MCP server that indexes your codebase into a knowledge graph so AI agents (Claude, Cursor, Copilot) can search and navigate it without burning tokens.
Search, read and write your self-hosted Open Notebook knowledge base from an AI assistant.
BuilderForce Agent Memory — MCP transport. Exposes @seanhogg/builderforce-memory to any MCP client (Claude Agent SDK in-process, stdio, or HTTP) over a pluggable MemoryBackend, with token-saving fetch
Public chat and shared memory for AI agents. Open reads, free write keys. MCP + A2A + WebSocket.
Secure, fragment-based long-term memory for MCP-compatible AI agents.
Public source-linked memories for AI agents: search, read, cite, reply, and share findings.
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
A semantic search engine for files and code.
Persistent AI memory using orbital mechanics. 100% local, zero API keys, MCP-native.
Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP.
A fully local MCP server for long-term memory with semantic search
VaultCrux Memory Core — 32 tools: knowledge, decisions, constraints, signals, coverage
Seeds, governs and navigates a memory_bank knowledge base: gated writes, routing, drift vs code
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
Local-first, file-native long-term memory hub: preflight, compact context injection, citations, human-approved commits, temporal validity, dedupe/merge, retrospective reflection, write-risk flags, a d
Coding-agent CLI with a code knowledge graph, memory and reviewable skills / CLI de agente de código com grafo de conhecimento, memória e skills revisáveis
Local-first persistent memory for AI agents over MCP. Ground truths, a failure firewall that blocks repeated mistakes (negative learning), and hybrid recall, stored in SQLite on your machine. No cloud
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
AI agent memory & knowledge graph, hosted in Germany (GDPR). Recall, relations, store via MCP.
Persistent, harness-agnostic session memory for AI coding CLIs (Claude Code, Codex, Gemini, Cursor, opencode, omp). One Markdown vault, any harness.
Search real problems, solutions, failed approaches and observed outcomes shared by AI agents.
Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.
Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).
Project knowledge graph with history-checked belief staleness, changeset proposals, cost reporting
AINative ZeroDB MCP Server - 93 operations for vector search, TurboQuant vector compression (PolarQuant + QJL), NoSQL, dedicated PostgreSQL management, files, events, RLHF, knowledge graph (entities,
Semantic knowledge graph for Obsidian with graph, classification and hierarchy modes, local embeddings, semantic bridge discovery and drift detection.
A second brain your AI assistants share: your notes, chats and mail, and memories kept as Markdown.
Memory: persistent memory for AI coding agents — a local-first SQLite brain, optionally replicated to the cloud, that survives sessions and compactions and is shared over MCP. This package plugs it in
Tool-agnostic AI development framework. Standardize projects across Claude Code, Cursor, Gemini, Codex, Windsurf, Copilot with automated templates, quality gates, persistent memory, and framework dete
A git-native personal AI memory layer: Markdown source of truth + MCP + topic-as-identity
Search and read the aicoolies catalog of AI and developer tools via a remote MCP knowledge graph.
Add MCP tools, OAuth, and a knowledge base to any Express app so AI clients can call your APIs
Memory for AI agents that knows what is still true. Typed bi-temporal facts, EU-hosted.
MCP server for comprehensive YouTrack integration: issues, work items with reports, user activity search, knowledge base, projects and users
Turn a folder of code/docs/papers into a queryable, persistent knowledge graph for AI coding assistants.
पूरी डायरेक्टरी
RAG, ग्राफ़ और एजेंट की लॉन्ग-टर्म मेमोरी। 2,656 सर्वर, सबसे ज़्यादा इस्तेमाल वाले पहले। हर एक पब्लिशर का पेज खोलता है।