--- schema: 1 type: video title: 'I Built a Personal AI Agent on a Raspberry Pi — Jeremy Adams, Neo4j' description: >- No Mac Mini, no laptop agent. Jeremy Adams runs his personal AI agent on an old Raspberry Pi he wears around his neck. Jeremy Adams, senior developer advocate at Neo4j, assembles a wearable AI agent live on stage: NanoClaw on a Raspberry Pi 4B, messaged over WhatsApp, with Docker-isolated agents and a Neo4j graph database. He shows how he built graph memory using the POLE schema (person, object, location, event) mid-flight, added voice-to-text through a USB mic and a hardware button, ran an offline mode with a local Neo4j, and walked the AI Engineer expo floor turning booth notes into a graph of themes. He finishes by upgrading to Neo4j Agent Memory. In this talk: • Why a small, hackable claw beats a feature-rich agent on your laptop • Connecting an agent to Neo4j over MCP • Graph memory with the POLE schema • Offline-first capture with a local graph that syncs and enriches in the cloud SPEAKER Jeremy Adams, Senior Developer Advocate, Neo4j LinkedIn: https://www.linkedin.com/in/jeremy-adams-pdx/ X: https://x.com/jpadamspdx GitHub: https://github.com/jpadams Website: https://jeremyadams.dev/ LINKS NanoClaw: https://github.com/qwibitai/nanoclaw Neo4j Agent Memory: https://neo4j.com/labs/agent-memory/ Agent Memory (GitHub): https://github.com/neo4j-labs/agent-memory GraphAcademy (free courses): https://graphacademy.neo4j.com/ CHAPTERS 0:00 Intro 0:12 Hi from Neo4j 1:32 What we're building 1:57 Live hardware setup 4:51 The Raspberry Pi claw boots up 6:06 Why small claws 8:05 Why NanoClaw 8:55 Architecture: WhatsApp → NanoClaw → Claude 9:40 Graphs 101 10:10 Querying Neo4j over MCP 10:50 Building memory on a plane: the POLE schema 12:15 Demo: the memory graph 13:29 Adding voice-to-text 14:49 Recording the expo booths 15:34 Offline mode with a local Neo4j 17:03 Enriching themes in the cloud 18:23 Upgrading to Neo4j Agent Memory 19:33 Get started with GraphAcademy Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #RaspberryPi #AgentMemory #AIEngineer canonical: 'https://liquidgold.cc/watch/oUZEt4EiPbk' markdown: 'https://liquidgold.cc/watch/oUZEt4EiPbk.md' llms: 'https://liquidgold.cc/watch/oUZEt4EiPbk/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-23T22:20:05.709Z' language: null children: [] videoId: oUZEt4EiPbk durationSeconds: 1210 publishedAt: '2026-10-03T16:30:34.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 12 endSeconds: 23 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=12' heldReason: rights - ordinal: 1 text: null startSeconds: 23 endSeconds: 102 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=23' heldReason: rights - ordinal: 2 text: null startSeconds: 102 endSeconds: 112 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=102' heldReason: rights - ordinal: 3 text: null startSeconds: 112 endSeconds: 122 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=112' heldReason: rights - ordinal: 4 text: null startSeconds: 122 endSeconds: 134 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=122' heldReason: rights - ordinal: 5 text: null startSeconds: 134 endSeconds: 297 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=134' heldReason: rights - ordinal: 6 text: null startSeconds: 297 endSeconds: 308 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=297' heldReason: rights - ordinal: 7 text: null startSeconds: 308 endSeconds: 374 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=308' heldReason: rights - ordinal: 8 text: null startSeconds: 374 endSeconds: 385 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=374' heldReason: rights - ordinal: 9 text: null startSeconds: 385 endSeconds: 485 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=385' heldReason: rights - ordinal: 10 text: null startSeconds: 485 endSeconds: 496 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=485' heldReason: rights - ordinal: 11 text: null startSeconds: 496 endSeconds: 542 watch: 'https://liquidgold.cc/watch/oUZEt4EiPbk?t=496' heldReason: rights --- # I Built a Personal AI Agent on a Raspberry Pi — Jeremy Adams, Neo4j No Mac Mini, no laptop agent. Jeremy Adams runs his personal AI agent on an old Raspberry Pi he wears around his neck. Jeremy Adams, senior developer advocate at Neo4j, assembles a wearable AI agent live on stage: NanoClaw on a Raspberry Pi 4B, messaged over WhatsApp, with Docker-isolated agents and a Neo4j graph database. He shows how he built graph memory using the POLE schema (person, object, location, event) mid-flight, added voice-to-text through a USB mic and a hardware button, ran an offline mode with a local Neo4j, and walked the AI Engineer expo floor turning booth notes into a graph of themes. He finishes by upgrading to Neo4j Agent Memory. In this talk: • Why a small, hackable claw beats a feature-rich agent on your laptop • Connecting an agent to Neo4j over MCP • Graph memory with the POLE schema • Offline-first capture with a local graph that syncs and enriches in the cloud SPEAKER Jeremy Adams, Senior Developer Advocate, Neo4j LinkedIn: https://www.linkedin.com/in/jeremy-adams-pdx/ X: https://x.com/jpadamspdx GitHub: https://github.com/jpadams Website: https://jeremyadams.dev/ LINKS NanoClaw: https://github.com/qwibitai/nanoclaw Neo4j Agent Memory: https://neo4j.com/labs/agent-memory/ Agent Memory (GitHub): https://github.com/neo4j-labs/agent-memory GraphAcademy (free courses): https://graphacademy.neo4j.com/ CHAPTERS 0:00 Intro 0:12 Hi from Neo4j 1:32 What we're building 1:57 Live hardware setup 4:51 The Raspberry Pi claw boots up 6:06 Why small claws 8:05 Why NanoClaw 8:55 Architecture: WhatsApp → NanoClaw → Claude 9:40 Graphs 101 10:10 Querying Neo4j over MCP 10:50 Building memory on a plane: the POLE schema 12:15 Demo: the memory graph 13:29 Adding voice-to-text 14:49 Recording the expo booths 15:34 Offline mode with a local Neo4j 17:03 Enriching themes in the cloud 18:23 Upgrading to Neo4j Agent Memory 19:33 Get started with GraphAcademy Recorded at the AI Engineer World's Fair 2026 in San Francisco. Subscribe for more talks from the engineers building with AI. AI Engineer: https://ai.engineer YouTube: https://www.youtube.com/@aiDotEngineer X: https://x.com/aiDotEngineer LinkedIn: https://www.linkedin.com/company/aidotengineer/ #RaspberryPi #AgentMemory #AIEngineer Canonical: https://liquidgold.cc/watch/oUZEt4EiPbk · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.