Free workshop walks through building an LLM Wiki for agent long-term memory
Al_Grigor · x · 2026-09-22
Paul Iusztin's hands-on workshop with DataTalks.club — building an LLM Wiki for agent long-term memory — is now publicly available. It drew 541 signups, 150 live viewers, and 8,500+ YouTube views.
The session breaks down, from first principles, how to give agents persistent memory without stuffing everything into the context window or setting up complex databases:
- Markdown-based knowledge graphs
- Progressive context disclosure
- Token-efficient memory layers
- Full implementation walk-through, from concepts to working system
A practical resource for developers who want agents with long-term memory using a lightweight, file-based approach.
More from coding & agent
- Cloudflare launches Worker Previews: isolated production-like envs for every Git branch — iannuttall · 2026-09-22
- 'A Summer of AI Optimization': Veteran Engineer Reports Major Speedups in Widely Used Libraries — austinvhuang · 2026-09-22
- The 'chief of staff' pattern: how agentic coding scales past context windows — arpit_bhayani · 2026-09-22
- Jay Alammar and Team to Host Free AI Agents Masterclass on Sept 29 — JayAlammar · 2026-09-22
- Hands-on: testing Grok 4.7 coding in Cursor across 4 real projects with cost breakdown — Arindam_1729 · 2026-09-22
- Agent did nothing, reported success, and passed: why agent-generated evidence isn't evidence — Muted_Ad_9442 · 2026-09-22