USDA FoodData Central nutrition data — search 1M+ foods, get full nutrition profiles (macros, vitamins, minerals), and compare foods side-by-side. Public domain government data.
Agent operations platform with 20+ tools for AI agents. Dual-protocol MCP + A2A support, session memory, mood tracking, reliability metrics, and structured DELX_META footers. Built for production agent workflows.
**Memxus** is multi-platform persistent memory for AI assistants. Save project context, preferences, and decisions once — recall them in Claude, ChatGPT, Cursor, and other MCP clients. ## What it does - **Remember** — store facts, preferences, and project context with collections and tags - **Recall** — semantic search across your memories - **Get context** — formatted context blocks for the current topic - **Manage** — list, inspect, update scope, and delete memories ## Co
Maintain persistent project context by storing decisions, lessons, and task checkpoints for seamless session transitions. Navigate information through semantic search and relationship graphs to uncover related knowledge clusters. Automate memory consolidation and cleanup to keep your workspace organized and relevant.
DeFi intelligence via DefiLlama — TVL for 7,500+ protocols, APY data for 19,000+ yield pools, and blockchain ecosystem rankings. Filter by chain, project, token, or minimum APY.
Persistent memory for AI coding agents. Store decisions, lessons, error patterns, and task checkpoints, then retrieve them via semantic search or graph traversal. Features session briefings, memory consolidation, time-based reminders, encrypted profiles, and knowledge compaction. Works with Claude Code, Cursor, Windsurf, VS Code, and any MCP-compatible client. #1 on LongMemEval benchmark (95.4%). Install: pip install omega-memory && omega setup
AI session memory: the brief your AI reads before every session so no session starts cold. Loads your project's current task, recent decisions, and open questions across Claude, ChatGPT, Cursor, and Codex.
Location intelligence — geocoding & reverse geocoding (OpenStreetMap), weather forecasts (Open-Meteo), timezone lookup, and Point of Interest search (restaurants, hotels, hospitals, 20+ types).
Enforce consistent C++ style and best practices across your codebase. Analyze naming, memory safety, and const correctness, and get actionable modernization suggestions up to C++23. Accelerate reviews with ready-made prompts and quick access to curated guidelines.
Authoritative time intelligence — current time in 597 timezones, sunrise/sunset/twilight times by location (US Naval Observatory), and moon phase calendar. Essential for scientific, agricultural, and scheduling agents.
LLM provider intelligence for AI agents. Get ranked recommendations for your task type, compare pricing and capabilities. Tools: recommend_llm, list_providers, check_provider_status.
AI trading memory layer for MT5/forex. 3-tier architecture (L1 raw trades → L2 pattern discovery → L3 strategy adjustment). 15 MCP tools: store/recall trades, performance analytics, reflections, evolution engine, and Outcome-Weighted Memory (OWM).
Persistent cron scheduler for AI agents. Schedule tasks that run even when your session ends — up to 30 days. Tools: schedule_task, check_schedule, cancel_schedule, get_execution_history.
Persistent AI memory layer for developers. Never re-explain your stack to AI tools again. Conxt captures your decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf — and surfaces them automatically at the start of every new session. **8 MCP tools:** - [get_context](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:223:0-255:52) — load relevant memories for the current task - [get_memories
Emercoin Agent Gateway — give your AI agent a verifiable on-chain identity and durable memory on the Emercoin blockchain (NVS). Register a GitHub-rooted identity and store tamper-evident hashes of your research and artifacts. OAuth login, no install. Neutral and provider-independent — not tied to any single AI vendor. FREE
Younanix Memory MCP gives autonomous AI agents access to real-world engineering memory from actual incidents (Slack threads + GitHub issues in Supabase, TRPC, Drizzle, Rails, Node.js etc). Natural language tool: query_lessons (search for problems, root causes, solutions). Structured output: {problem, root_cause, lesson_learned, confidence (80-100%), category, tags}. Free preview: 1 query/hour (degraded results). Full access: $0.10/query via x402/USDC micropayments (perm
16 tools for persistent agent memory via MCP. Profiles, signals, timeline events, work items, and multi-agent coordination backed by Upstash Redis — for Claude Desktop, Cursor, Cline, Windsurf, and any MCP-compatible AI tool.
SEC EDGAR filing intelligence for AI agents. Get insider trading (Form 4), earnings data (XBRL), material events (8-K), and recent filings for any public company.
Undisk MCP: safe file memory for AI agents. Every write creates an immutable version. Any file restored in <50 ms. AI makes mistakes, so Undisk keeps recovery instant. Policy guardrails, secret detection, and tamper-evident audit trails. MCP-native.
AI conversation memory that works everywhere. Save and recall conversations across Claude, ChatGPT, Gemini, Cursor, and all MCP-compatible platforms. 11 tools including semantic search, cross-platform discovery, shared community memories, and memory-powered workflows. Your AI knows who you are before you say a word.
Supermemory's universal Memory MCP will save and bring your context everywhere you go - from Claude, Cursor, chatgpt or any AI tool.
Ratary is an AI Brain Platform — infrastructure that gives AI: Persistent memory — durable, owner-scoped, versioned Structured knowledge — metadata, relations, graph traversal Intelligent retrieval — hybrid search + bounded context assembly Protocol access — Ratary MCP, REST, optional gRPC It sits between AI clients and storage. One brain, many surfaces — Cursor, Claude Code, custom agents, enterprise APIs, and remote MCP hosts. The runnable deployment is Ratary Server — th
Synapse Layer — persistent, encrypted memory for autonomous AI agents. MCP‑native, audit‑ready, and compliant for regulated teams.
datamcp is a hosted Model Context Protocol gateway for PostgreSQL 12+, MySQL, OpenAPI 3.x/Swagger, and Agent Memory. Create scoped remote MCP links for Claude, Cursor, ChatGPT, Codex, VS Code, and other compatible clients. Keep source credentials server-side, restrict database operations or API methods per link, and use structured shared project memory with full-text search, compact handoffs, scoped writes, and reviewed canonical Rules and Project Summary updates. MCP clients
Mitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth.
Cryptographic spatial proof-of-presence for AV fleets, logistics, AR. 91% spoof detection.
Person-owned AI memory that learns, not just stores — portable context for any MCP client.
Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.
One memory, every AI: Claude, ChatGPT, Perplexity, Gemini, Cursor, OpenClaw, Hermes, any MCP client.
Shared project context for AI agents and teams: docs, tasks, and messages that stay current.
Serve a secret to an agent exactly N times from locked RAM, then wipe it and self-destruct.
**Your agent doesn't ask for memory. It uses it.** The moment Sync connects, Claude, Cursor, VS Code, and Zed start checking it before every task — and writing to it after every decision. No *"look it up."* No *"remember this."* The protocol handles it. What that means in practice: - Decisions made on Tuesday survive Friday's new chat - A teammate's agent picks up exactly where yours left off - The same context follows you across every editor you use - A new person on the
Persistent AI memory for Claude Code, Cursor, Copilot, Windsurf, Cline & Zed. Your AI remembers every lesson, fix, and architecture decision — across sessions, IDEs, and model upgrades. Quality-aware recall beats raw BM25 keyword search by **+33% Precision@1** on our published benchmark. Features causal root-cause analysis (causal_trace), failure prediction (brain_predict), git-ambient learning (brain_from_git), shared Team Brain, and Memory Crystals. BM25+ search in 11 lan
MemBridge Memory MCP Server allows you to share your memory across multiple AI tools like Claude, ChatGPT, Cursor, and more. You save information once, and it becomes accessible from any AI tool you use. This eliminates the need to repeat the same context every time you switch tools.
Give Claude, Cursor, and every MCP client one shared memory that never leaves your machine. On-device vector search via LanceDB + Transformers.js (384-dim embeddings), AES-256-GCM client-side encryption, and write-behind ciphertext sync. ### What you can do 🧠 **Store memory** — embed and persist any context fact on-device. Automatic de-duplication, PII redaction, and write-behind encrypted sync. 🔍 **Recall memory** — semantic search over stored context. 10 ms warm recall, 0
capture is a memory layer that ingests emails, Slack threads, web pages, LinkedIn posts, and documents, then makes them queryable by any MCP-compatible AI assistant. Connect your MCP server URL to Claude, Cursor, or any agent and your entire captured knowledge base becomes available in context — instantly. Capture also extracts decisions, action items, and project history so agents can get up to speed without interrupting your team. No extra workflow required. Forward an em