Syncnapse
2026
AI meeting teammate that builds governed company memory
Overview
Winner of the Founder Mode track at Agentic AI Build Week, one of the biggest agentic AI hackathons in the region, organized by GenAI Fund with AWS, VNG, and Tencent Cloud. Around 2,500 builders and 300+ teams pitched across the week in Ho Chi Minh City.
Syncnapse is an AI teammate that actually joins your meetings. It is not a recap tool that emails you bullets afterward. It is a real participant in Google Meet, Zoom, and Teams that you can talk to, that talks back, and that remembers. It captures not just what was said, but why decisions were made and who owns what, and turns all of it into governed company memory that is searchable, permissioned, and owned by the company instead of trapped in one person's head. When a task comes out of a meeting, it recommends whether that task should go to a human, an AI agent, or both, with actual reasoning attached. Built with my team, We Maid AI.
Under the hood, Syncnapse is a Turborepo monorepo (TypeScript, Node 22) running two distinct agent runtimes. The first is a chat-turn tool loop over the memory graph. The second is a real-time live meeting harness that takes raw audio through voice activity detection, speech-to-text, addressing and floor control, an LLM orchestrator, and finally text-to-speech, and it can run multiple bots at once with org-chart supervisor delegation. Recall.ai bots join the calls, and a Chrome extension (MV3, built with WXT) detects meeting tabs. A Hono and oRPC backend with Better Auth organizations persists everything to Postgres with pgvector (HNSW) through Drizzle, then ElectricSQL streams it back down into PGLite inside the React 19 TanStack Start dashboard, with Loro CRDT handling multi-agent merges. Governance is the core invariant: AI proposes, humans approve. Every memory write flows through a proposal state machine with versioning and audit trails, and the system integrates with Slack, Linear, and MCP through a save_to_synapse server. The whole stack is Dockerized and deployed on Railway.
Screens
Stack
Notes
Syncnapse (2026) is Phuoc's latest project: an AI teammate that joins meetings as a real participant in Google Meet, Zoom, and Microsoft Teams. You can talk to it, it talks back, and it remembers. Built with team We Maid AI (Giang Tran Minh, Simon Nguyen, Thanh Nam Vu, Son Ngo, Catherine Pham), it won the Founder Mode track at Agentic AI Build Week, one of the region's biggest agentic AI hackathons, organized by GenAI Fund with AWS, VNG, and Tencent Cloud, with around 2,500 builders and 300+ teams pitching in Ho Chi Minh City.
Syncnapse solves the problem that a company's most valuable knowledge lives in people's heads, private AI chats, and meetings, and vanishes when people leave. It captures not just what was said but why decisions were made and who owns what, turning it into governed company memory that is searchable, permissioned, and owned by the company. When a task comes out of a meeting, Syncnapse recommends whether it should go to a human, an AI agent, or both, with reasoning attached.
Syncnapse's tech stack: a Turborepo + pnpm monorepo (TypeScript ESM, Node 22) with a React 19 TanStack Start dashboard, Hono + oRPC typed backend, Better Auth with organization multi-tenancy, Postgres + pgvector (HNSW) via Drizzle ORM, ElectricSQL read-path streaming into client-side PGLite with Loro CRDT multi-agent merge, Recall.ai meeting bots, a Chrome MV3 (WXT) extension for meeting-tab detection, OpenAI GPT + text-embedding-3-small, Whisper STT + OpenAI TTS for live voice, and object storage on local filesystem or Cloudflare R2. It is deployed on Railway (Dockerized).
Syncnapse has two distinct agent runtimes: a chat-turn tool loop over the memory graph (search_memory, propose_memory) and a real-time live-meeting harness (audio → VAD → STT → addressing → floor control → LLM orchestrator → TTS) that can run multiple bots with org-chart supervisor delegation. Its core governance invariant is 'AI proposes, humans approve': every memory write flows through a proposal state machine with versioning and audit trails. It integrates with Slack and Linear for workflow automation and exposes a save_to_synapse MCP server.