ai-netcafe
Verified · 17 days agoTables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.
Persistent code memory for AI agents: notes pinned to files and symbols that survive refactors.
claude mcp add anchordb -- docker run -i --rm ghcr.io/jolovicdev/anchor-db:1.0.6
AnchorDB is a developer-facing memory layer that pins notes to files and symbols so agent context can survive renames and refactors. It is aimed at teams building coding agents or long-running AI workflows around source code. The idea is practical, but with no visible adoption signals here it reads as an early-stage utility that needs real-world validation.
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.