Auditable memory (memory3l)
Audited memory over MCP: an append-only fact ledger plus verifiable invariants I1-I5.
Open the source (opens registry.modelcontextprotocol.io) https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.jayzht/memory3l-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.jayzht.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
memory3l-mcp@0.2.0
From the server's entry in the official MCP Registry
Settings it asks for
MEMORY3L_ROOT· Override the location of the memory3l audit core (development against a source checkout).MEMORY3L_DB· Path to the SQLite fact-ledger file to serve.MEMORY3L_ALLOW_WRITE· Set to 1 to also expose the append_facts tool.
Related
-
Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.
inspeximus@3.27.0 -
memory-eternal
MCP servers🧠 给 AI 一个可信的第二大脑:本地 SQLite · 先审核再入库 · 不可篡改审计 · 记忆账本。🕷 蜘蛛侠皮肤 · 🔍 自建集 R@5 99.1% / LongMemEval-S 97.2% · 🧩 一个库接入 DSH / Claude Code / Codex / Cursor / 任意 MCP · ⭐ MIT 开源 · 🚀 零依赖开箱即用
git clone https://github.com/EternalNight996/memory-eternal.git -
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
tradememory-protocol
MCP serversTamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
tradememory-protocol@0.5.6 -
caura
MCP serversCaura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
git clone https://github.com/caura-ai/caura.git -
mnemosyne
MCP serversAuditable, local-first memory for AI agents in one SQLite file. MCP server for Claude Code, Cursor and Codex. npm: mnemosy-ai
git clone https://github.com/28naem-del/mnemosyne.git