Memory & Knowledge MCP Servers for DeepSeek Harness

A second brain for your AI assistant: remembers your work, plans your day, encrypted with your key.

Checkpoint and resume for AI agent runs, so crashed runs pick up where they left off.

Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.

Long-term memory for AI agents. Pass one sentence, and it remembers, recalls, or forgets.

A notebook your coding agents write to: notes that track the code's commit, and handoffs.

The context layer for the physical world: filmed spaces as cited context for agents.

Agent memory that refuses to guess: evidence-gated recall, exact-source reads, verifiable deletion.

Bi-temporal AI memory. 56 tools, knowledge graph, semantic search. EU-hosted, free tier.

Local-first memory for AI agents: recall with sources, answer checks, documents, mesh, governance.

Local-first memory for AI agents: markdown source of truth, budget-aware recall, write gate.

Memory for every AI you connect, tied to your account: recall, search, remember. OAuth sign-in.

Shared semantic graph for AI reviews, classification and structured memory across AI assistants.

Search and read your own notes: insights, drafts, book and podcast notes. Read-only, OAuth.

Read and write in your Whatcha diaries, including exchange diaries shared with a partner.