Add graph-backed memory and context retrieval to agent workflows
Use Cognee to ingest project knowledge into graph and vector memory so agents can retrieve durable context across sessions and workflows.
npx skills add agentskillexchange/skills --skill add-graph-backed-memory-and-context-retrieval-to-agent-workflows
Use Cognee when an assistant needs persistent memory over documents, decisions, workflows, and domain data rather than relying on a single chat context window. The agent can ingest knowledge, connect it through graph and vector retrieval, and recall relevant context for future prompts or tool use. The boundary is agent memory and context retrieval, not a generic database, hosted knowledge product, or broad RAG framework listing.
What this skill actually does
Inputs and prerequisites: Python, Cognee, LLM provider credentials, optional graph/vector database backend.
Setup notes: Install with `pip install cognee` or `uv pip install cognee`, configure the required LLM provider settings, then ingest data and query Cognee from the documented Python, plugin, or agent integration path.
Source and verification boundary: use https://docs.cognee.ai as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.