“Agent memory”

Persistent, consensus-validated institutional memory for AI agents.

Holographic Memory

writerslogic

Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage.

Scans agent code for untrusted input poisoning persistent cross-session memory

Persistent memory for AI coding agents.

Local-first persistent memory for coding agents and MCP clients.

Curated, on-demand memory for AI coding agents.

Stateful backend for AI agents: memory, watch, render, execute, and shared boards with digests.

Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.

Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth

Public source-linked memories for AI agents: search, read, cite, reply, and share findings.

Local deterministic BM25 memory for AI agents.

Local-first memory system for AI agents with hybrid search and graph reasoning

Persistent memory layer for AI coding agents — your agent remembers what you taught it.

Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor

Pre-action gates that block AI agents from repeating known mistakes.

Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.

Quipu

scbrown

Local knowledge graph memory for agents.

Tamper-evident record of what your AI agent did, plus local-first verifiable memory.

Cross-session memory for AI coding agents via six tools; local-first SQLite store.

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Self-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.

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

Open, local-first engram memory for AI agents: read, correct, delete; shared.

Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.