AI and memory

Local-first shared memory for multiple AI agents that compounds with use; Markdown + git, MCP + CLI.

Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.

Project memory across sessions for AI agents. A queryable decision log in the repo.

Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.

Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

Guardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.

Token-light local memory with SQLite hybrid retrieval for MCP agents.

Automatic project memory for Claude Code and Cursor; Codex and Claude Desktop over MCP.

Give any agent self-improving memory you can trust in production. Built-in memory security.

Local codebase memory and repository code search for Codex, Claude Code, and MCP coding agents.

Shrink images to a token budget for vision LLM agents and pipelines. Not for chat-pasted images.

Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files.

Governed MCP orchestration, tamper-evident memory, and Claude Code Seatbelt hooks.

Encrypted, local memory for Claude, Codex/ChatGPT and Copilot. Needs the free Vitkilabs Anvil app.

Long-term memory for AI coding agents, stored as a tree of plain local files.

AI session memory: the brief your AI reads before every session so no session starts cold.

Persistent decision memory for agents — learns which action works in which context

Search, read and grow a Karpathy-style LLM wiki of linked Markdown pages, with cited answers.

Local-first memory of how you write: style profile and real reply examples from your chat exports

AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

Local-first memory for Claude Code, Codex and Claude Desktop, kept verbatim on your own PC.

MCP server for AI dialogue using various LLM models via AceDataCloud

Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.