ai-netcafe
Verified · 21 days agoTables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.
Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).
claude mcp add mnemex -- uvx mnemex
Implements a memory layer for AI agents with decay and reinforcement semantics, backed by simple JSONL and Markdown storage. That makes it interesting for experimenters who want inspectable local memory behavior, but it still looks like a niche building block and likely needs careful testing before being trusted in production agent systems.
Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.
Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
MCP server for filesystem access
MCP server for terminal commands, file operations, and process management
Local-first knowledge management with bi-directional LLM sync via Markdown files.
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.