Add graph-backed memory and context retrieval to agent workflows
SkillDocs & knowledgeGive your AI a lasting memory of your project. It uses Cognee to ingest project knowledge into graph and vector memory, so your AI can retrieve durable context across sessions and workflows instead of starting over each time.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, start by having your AI ingest your project knowledge into memory. Once stored, it can draw on that context in your ongoing sessions and workflows.
Then ask your AI: use the Add graph-backed memory and context retrieval to agent workflows skill
What your AI can do with it
- Ingest project knowledge into graph and vector memory
- Recall stored project knowledge in later sessions
- Retrieve durable context during workflows
- Carry context from past sessions into new tasks
What this skill tells your AI
The instructions your AI receives, as published by agentskillexchange/skills in skills/add-graph-backed-memory-and-context-retrieval-to-agent-workflows/SKILL.md and read by ahel’s review.
Use Cognee to ingest project knowledge into graph and vector memory so agents can retrieve durable context across sessions and workflows.
Prerequisites
Python, Cognee, LLM provider credentials, optional graph/vector database backend
Installation
Prerequisite: Python 3.10 to 3.14.
Install Cognee with uv or pip:
- uv pip install cognee
- pip install cognee
For Claude Code persistent memory, upstream documents installing the Cognee integration plugin:
-
claude plugin marketplace add topoteretes/cognee-integrations
-
claude plugin install cognee-memory@cognee
-
Extracted from upstream docs: https://raw.githubusercontent.com/topoteretes/cognee/HEAD/README.md
Documentation
Source
Signals
- GitHub stars
- 38
- Forks
- 53
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
add-graph-backed-memory-and-context-retrieval-to-age-05ek6fe- Source
- github.com/agentskillexchange/skills