AI and memory

37Trust score 37 of 100, Limited

Persistent shared memory for AI agents, with verified writes and a transcript tier.

Local-first AI memory with causal graphs. Fully offline, zero config, your data stays local.

AI LLM with Gemini, MiniMax, Replicate, OpenRouter. Vision, search, code review. USDC on Base.

37Trust score 37 of 100, Limited

Find out who killed Claude by interrogating the LLM driven suspects...

Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.

Persistent memory and knowledge graph for AI assistants — keyword + vector + graph search.

37Trust score 37 of 100, Limited

Skybridge Example App showcasing a Time's up game with the LLM

Public MCP server for the LLM Search Engine

Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.

Hand a project over with the reasons attached. Local-first cross-agent memory MCP + drift detection.

Local-first, source-traceable agent memory — no LLM at ingest, fully offline

Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

Generate and edit images from your coding agent with Gemini and OpenAI, using your own API keys.

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

Seeds, governs and navigates a memory_bank knowledge base: gated writes, routing, drift vs code

MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.

MCP server for AI memory management using Letta - Standard MCP format

RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.

MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

An MCP server that provides visual memory and context storage with knowledge graph capabilities

Prices, context windows, lifecycle and deprecation dates for 270+ AI/LLM models. Daily, no key.

Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search

On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.