Cross-platform local MCP server and CLI for bitemporal long-term memory for AI agents
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mnemo-mcp-agent","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Mnemo > **Production-Ready Cognitive Long-Term Memory & Code Knowledge Graph for AI Agents** > *Zero-Infrastructure, Local-First Model Context Protocol (MCP) Server and CLI.* [](https://pypi.org/project/mnemo-mcp-agent/) [](pyproject.toml) [](src/mnemo/storage/) [](https://modelcontextprotocol.io/) [](LICENSE) [](pyproject.toml) --- ## Overview **Mnemo** provides persistent, cross-session architectural memory and an autonomous code knowledge graph for AI coding agents. Unlike ephemeral prompt windows or naive vector-only RAG, Mnemo is an autonomous cognitive subsystem built directly on local SQLite. It links natural-language rules and decisions directly to code entities, automatically detects architectural code drift, models memory retention through codebase activity ticks, executes true bitemporal point-in-time queries, and retrieves knowledge through a 3-channel Reciprocal Rank Fusion (RRF) search engine. ``` ┌──────────────────────────────────────────────┐ │ AI Coding Agent / IDE │ └──────────────────────┬───────────────────────┘ │ MCP Protocol (JSON-RPC) ▼ ┌────────────────────────────────────────────────────────────────────────────────────────────────────────┐ │ MNEMO SUBSYSTEM │ │ …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.