Qdrant Hackathon: Building an AI Memory Layer for Slack via Knowledge Graphs
qdrant_engine · x · 2026-08-13
Qdrant and Cognee are hosting a hack night in Berlin on August 14, focused on building an AI agent memory layer for Slack workspaces.
Background: Most agent memory today relies on simple Markdown files, which break down when dealing with team sharing, long context windows, and complex permissions.
What to Build: Participants will use Cognee's memory engine and Qdrant's vector search to build a complete pipeline:
- Ingest messages and threads from Slack
- Structure history into a knowledge graph with provenance
- Answer complex questions beyond simple keyword search
- Compile patterns into reusable agentic SKILLs
More from coding & agent
- Tutorial: Configure Grok 4.6 as a Subagent in Claude Code and Codex — daniel_mac8 · 2026-08-13
- Accidental £500 Overage on Top of Cursor Subscription — BlackHC · 2026-08-13
- Amp Coding Assistant Now Supports Grok 4.6 — HankYeomans · 2026-08-13
- Appwrite CLI Migrates from TypeScript to Go: 17x Faster Startup, 1/10 Memory — rseroter · 2026-08-13
- Building a Concert Playlist Generator with Claude Code and Codex — cocktailpeanut · 2026-08-13
- Dev Reflects on AI Coding: Models Make Basic Reasoning Errors, Hand-Coding Wins — jsuarez · 2026-08-13