Certified SEC EDGAR fact memory for AI agents with zero hallucination and cryptographic filing provenance. Grounded directly to official SEC 10-K/10-Q filings with sub-25ms retrieval across 4.06M certified cells.
**LLMtoMD is the memory layer for AI coding agents.** It converts any document — PDF, DOCX, slides, spreadsheets, images, audio, even whole websites — into clean, structured Markdown, then exposes it over MCP so your agent can **search your FRDs, specs, and API docs on demand** instead of re-reading (or forgetting) them. On a real 50-page spec, answering a question via retrieval used **~97% fewer tokens** than holding the whole doc in context — and returned the exact, cited
Deterministic pay-per-call tools for AI agents: live web search and cited answers, news, browser render, market data, speech-to-text, wallet-keyed memory, plus 500+ long-tail tools via find_tool. Settle in USDC via x402 or free via proof-of-work. Maintained by Havok Holdings LLC.
Solves memory loss for AI agents operating across multiple calls. Store, recall and audit long-term memory with AES-256 encryption. Includes SHA256 deletion audit proof. x402 USDC pay-per-call. Japanese language support included.
Your portable, growing memory for AI. EU-hosted personal knowledge layer: serves your AI-self files (identity, voice, rules) and learned patterns to any MCP client. Read-only by default; save-lesson only on your explicit ask. OAuth 2.1.
Persistent cloud memory for Ai coding assistants. 33 MCP tools, 85% accuracy on LoCoMo benchmark. Semantic search, auto-skills, knowledge graph, quantum-safe encryption. Your Ai remembers everything across sessions, editors, and machines.
Persistent epistemic memory and sub-5ms associative recall on the Volumetric Lattice Network for AI agents and LLMs with zero context decay. ### Key Capabilities: - **Reduce Context windows up to 90%** - **Sub-5ms Recall:** $O(1)$ topological associative recall across infinite context. - **Zero Attention Decay:** Ingest documents and conversations into permanent simplicial lattice nodes without loss. - **Deterministic Quotes:** Verbatim quote retrieval without LLM token diff
**Run your job search from any AI assistant.** Refine gives an agent real actions on a job search plus durable memory that persists across sessions and assistants. - **A model of you.** `get_persona` returns your inferred preferences, seniority, and dealbreakers, so every opening, reply, and recommendation is scored and tailored to you. - **Real openings, ranked.** Track companies, browse matched openings, and get adjacent-company recommendations, all scored fo
Glazyr Viz bypasses fragile DOM scraping and Cloudflare blocks by feeding raw Chromium memory frames directly to your AI agent. Achieve 177 FPS zero-copy vision with built-in, agent-native USDC compute settlement. The Screenshot Tax is over.
Persistent semantic memory for AI assistants. Same memory from Claude, ChatGPT or any MCP client: your AI remembers your work, decisions and conversations across sessions, devices and models. Unlike plain RAG or note archives, every write passes a server-side **quality gate** that rejects redundant memories (~80% of proposals in production), contradictions are tracked as first-class objects instead of being silently swallowed, and every answer can cite its sources. - **Zero
**Agent memory that survives you — durable, wallet-addressed, free to start.** No signup, no API key, no payment: any EVM keypair is a working account with a free tier (256KB) that covers real agent state. You are a process, not a server: when your session ends, your state ends with it. The Locker keeps what must persist, and a fresh process holding *only* your wallet key recovers it byte-for-byte — across sessions, machines, and vendors. **Zero-ceremony MCP (recommended):*
Store and search user-specific memories to maintain context and enable informed decision-making based on past interactions. Seamlessly integrate memory capabilities into your AI tools with a simple and intuitive API. Enhance your agents with relevance-scored memory retrieval for improved contextual awareness.
# Motecloud Memory MCP Motecloud is durable memory infrastructure for AI agents. It gives MCP clients a shared, tenant-scoped memory layer for remembering facts, decisions, codebase context, task history, contradictions, and working-session notes across conversations and tools. Use Motecloud when your agent needs more than chat history: long-lived graph memory, hybrid semantic search, task context priming, real-time session capture, and safe memory writes with OAuth-based a
Knownbase gives AI agents durable, structured project memory that persists across sessions, tools, and workflows. Through MCP, agents can store and retrieve Markdown-based knowledge such as architecture decisions, debugging discoveries, implementation details, handoffs, project facts, and ongoing work. Notes can be organized by project, tags, status, and structured metadata, then searched efficiently using full-text queries and incremental last-modified filtering. Knownbase
Household finance memory, budgets, transactions, and monthly reviews for AI assistants. Give your LLM a financial advisory brain.
The media memory layer for AI agents and their humans. Your AI client gets 43 tools to search your collection, add items, update ratings, build cross-media lists, preview music, and find patterns across everything you've read, watched, played, and listened to.
Persistent, portable memory for AI assistants — a private per-tenant memory graph (memories, lessons, sessions, documents) reachable from any MCP client. Sign up at https://brainbox.thexi.dev.
Full control memory API for AI agents. Maindex Expert is the unrestricted interface to the Maindex memory layer. It exposes the full memory graph, including structured data, relationships, revision history, and provenance, so agents can read, write, and organize memory with precision. Unlike simplified memory tools, Expert provides direct access to how memory is stored and maintained: - Create, update, and delete structured memories - Search and filter across the full memo
Enhance your LLM applications with a scalable knowledge graph memory system. Utilize semantic search and temporal awareness to manage and retrieve information effectively, ensuring your agents have persistent and contextual memory capabilities.
Contexta gives AI assistants a persistent, typed memory layer backed by a knowledge graph. One tool call searches across keyword, vector, and graph indexes simultaneously — so your agent finds the right context whether it remembers a phrase, a concept, or a relationship between entities.
Manages long-term memory and cognitive state to enable personalized and consistent interactions. Builds complex knowledge graphs by connecting thoughts, insights, and facts for deep recall. Facilitates seamless context handoffs and artifact storage across different work sessions.
AI memory server with 56 MCP tools. Knowledge Graph, semantic search, session tracking, multi-agent support. Magic Link auth, EU hosted Frankfurt. Free tier available.
Persistent memory for AI agents. Memories decay with time, strengthen on recall, and connect through an entity graph. MCP compatible.
Persistent memory MCP for AI agents. AgentMemory helps AI agents store, retrieve, inspect, and reuse long-term memory, task history, workspace knowledge, and context across long-running workflows. Use it for AI agent memory, autonomous agent memory, persistent context, personal AI memory, workspace recall, and agent knowledge management. The server provides read-only MCP tools for site profile, health status, pricing, analytics summary, conversion funnel, checkout status, se
Updated 9-16-25 Fixed EV issues Connections should be solid! v3.1.0 GREAT NEWS: The server will now work for everyone - Railway users, Heroku users, Render users, etc.! ***ONLY ADD EVS that APPLY TO YOUR OWN INSTANCES - Leave Blank if unused - :) Update 9-15-25 v3.0 fixed semantic search temporal tool: Add this at the beginning of n8n workflows to give temporal context UPDATED 9/1/2025! NEW TOOLS! Use the Redis Stream tools with n8n MCP Client Node for use anywhere! The U
Every project you have going, on one board your coding agents keep current and you actually read. Other project-memory tools store context for the agent. This one is a board you open. Your agents read it at the start of a session and write back at the end, and when one hits a decision only you can make, it lands on your board instead of stalling the session. - **get_brief** at the start: what you're working on, what each project is waiting on, and which decisions are alre
DoneThat automatically tracks all work and uses this context to boost your productivity: Automated timesheets, long-term memory for AIs, proactive coaching, and social sharing for accountability and remote trust. DoneThat is built privacy-first, cross-platform, and takes five minutes to set up.
Hosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth.
Cross-tool AI memory that recalls first every turn and admits when it doesn't know. Every recall passes an anti-confabulation gate (answer | verify | abstain) — it abstains rather than guess. Eight tools: Memory Write, Memory Recall, Playbook Recall, Gated Recall (abstains when unsure), Verified Recall (high precision), Memory Feedback (label a recall decision), Memory Search, and Fetch Memory — full parameter-level reference at https://ultramemory.io/docs/tools/. Connect wit
WorkingMemory is a private, cloud-synced persistent memory that builds your personal knowledge base as you go, so you can stop re-explaining yourself when moving a task between AI chats.
Save, search, and format memories with semantic understanding. Enhance your memory management by leveraging advanced semantic search capabilities directly from Cline. Organize and retrieve your memories efficiently with structured formatting and detailed context.
Artel is a self-hosted, self-organizing mesh for AI agent fleets — shared memory with embeddings, session continuity (handoffs across context resets and machines), agent-to-agent messaging, tasks/events, cross-instance feed meshing with no central coordinator, and an async archivist that synthesizes connections no single agent can see. Any HTTP-capable agent participates: Claude Code, AutoGen, raw API scripts. **Hosted-backend model:** you deploy one Artel instance (Docker)
Stores important facts, decisions, and patterns for persistent access across different sessions. Retrieves relevant historical context instantly through semantic search to maintain continuity. Organizes your knowledge base by archiving outdated information while keeping the most useful insights accessible.
Simple memory for AI: keep, recall, update, and forget information across sessions. Maindex Smart is a user-controlled memory layer for AI assistants. It lets you persist useful information like preferences, decisions, notes, and project context, then retrieve it later without repeating yourself. Core tools: - keep — save something worth remembering - recall — find relevant memories when you need them - update — revise existing information - forget — remove or permanently d
MemoryRouter is a persistent AI memory layer delivered as an MCP memory server. Connect this server to Claude, ChatGPT, Cursor, or any MCP client and your assistant gets user-scoped, cross-AI memory: store memories, search them semantically, and carry context from one session and one tool to the next. Move useful context from ChatGPT to Claude, keep decisions and preferences across sessions, and give agents memory that survives compaction. Sign up at https://memoryrouter.ai,
Every agent debugs alone. Fixes die in the conversation. knownissue is the shared memory where they don't have to. When your agent hits a bug, it searches knownissue first. If another agent already solved it, yours gets the fix instantly. When your agent solves something new, it reports the fix so the next agent doesn't start from scratch. **5 tools:** - `search` — find known issues by error message or library context - `report` — report a new issue with an optio