# SSE Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/sse
> Markdown URL: https://aitinkerers.org/technologies/sse.md
> Technology record last updated: 2026-09-18T15:13:56Z
> Generated: 2026-09-23T06:48:12Z

SSE (Server-Sent Events) enables real-time, uni-directional data streaming from servers to browsers over standard HTTP.

SSE (Server-Sent Events) utilizes the EventSource API (standardized in HTML5) to establish a persistent, low-latency connection for server-to-client updates. It operates over standard HTTP/1.1 or HTTP/2: this bypasses complex firewall configurations and eliminates the overhead of WebSockets for one-way feeds. Engineers deploy it for high-frequency data (like live stock tickers or social media notifications) by setting the Content-Type header to text/event-stream. The protocol handles automatic reconnection natively: it uses structured fields (including data:, id:, and retry:) to ensure consistent delivery without manual polling or custom retry logic.

- Official technology site: https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events
- Public AI Tinkerers demos and talks: 4
- Result page: 1 of 1

## Recent Public Talks and Demos

### [SamePage: you and your agent, literally on the same page](https://columbus.aitinkerers.org/talks/rsvp_7Rnho8suGUw)

SamePage is a Rust library for adding agents to a UI responsibly: they join over the AG-UI protocol with full tracing and human approvals, so you don't rebuild that plumbing for every app you want AI in. It runs at several tiers, from a loose brainstorm room up to a surface where sign-offs are enforced. The point is aligning intent. We work with an agent across sessions until the intent lands in a PRD, then implementation drifts from it, small at first, compounding. Load the PRD into SamePage and the agent displays its understanding as objects on the page. We sign off on each one, and the parts that seemed clear but were misaligned surface immediately. This is one of the very few arenas where human and agent are actually looking at the same thing. Each sign-off then compiles into a machine-checked requirement, so alignment is enforced for the life of the repo, not just the meeting. Live demo: a room started from the terminal with zero build step, a coding agent attached over MCP authoring UI while we talk, my marks on its work read back as meaning instead of coordinates, and the event log showing exactly who did what.

- Event context: AI Tinkerers - Columbus September Meetup — 2026-09-07 — Columbus
- Public talk page: https://columbus.aitinkerers.org/talks/rsvp_7Rnho8suGUw

### [Does your coding harness actually do anything? Measuring it, fairly.](https://boston.aitinkerers.org/talks/rsvp_bx0CiDi1_uo)

Everyone's bolting "harnesses" onto coding agents — Superpowers, GSD, Agent-Skills, Compound Engineering — but does the scaffolding actually make the model build better software, or just feel better? CodingHarness.xyz is an open eval that pits these frameworks head-to-head: same spec, same model, isolated sandboxes, and an evidence-based rubric (does it meet the PRD? is the code any good?). I'll share the surprising result — an inverse-scaling effect lifted straight from a recent Xiaomi paper and reproduced on real runs: harnesses help most exactly where the base model is weakest, and barely at all where it's already strong. Even better, it's framework-dependent — one framework tracks the curve almost perfectly, another inverts it and only helps strong models. Live demo of the eval studio: watch two frameworks build the same app, stream the agent's work turn-by-turn, and see the marginal-gain scorecard light up green/red. Plus a sneak peek at turning framework competitions into a spectator sport (think FIFA bracket, but for coding agents).

- Event context: AI Tinkerers Boston: GTM Agentic AI Launch — 2026-06-29 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_bx0CiDi1_uo

### [Real-Time Web Scraping with AI Agents: No Puppeteer, No XPath, Just a Goal](https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_APx09m92Cf8)

Traditional scraping breaks every time a site updates its HTML. I'll show a different approach: give an AI agent a URL and a plain-English goal, and it figures out the page on its own. Live on stage: a hotel search app that sends Booking.com and Agoda URLs to Tinyfish agents. Each agent autonomously navigates the real site, handles dynamic content, and returns structured JSON — no CSS selectors, no brittle DOM parsing. II'll also show the Tinyfish run dashboard live so you can watch the agent clicking through pages in real time.

- Event context: AI Tinkerers Ho Chi Minh City: From Prompt to Agent — 2026-03-07 — Ho Chi Minh City
- Public talk page: https://ho-chi-minh-city.aitinkerers.org/talks/rsvp_APx09m92Cf8

### [Building a Persistent Memory & Stateful Second Brain AI Agent](https://dhaka.aitinkerers.org/talks/rsvp_kSMaLnvvGGg)

Demonstrating context engineering in practice through Slatekore - an open-source starter kit that gives Gemini CLI persistent memory using Obsidian as the storage layer. 1. State Management Without Infrastructure How to use the file system as persistent state - your Obsidian vault becomes both the agent's memory and its knowledge base. No databases, no vector stores, no MLOps. 2. Context Engineering for Agent Behavior Crafting system prompts (GEMINI.md) and workflow files that define agent capabilities, constraints, and multi-step reasoning patterns. The prompt is the agent's configuration. 3. Tool Use Through Natural Interfaces Connecting the agent to real actions: creating files, managing tasks, building knowledge graphs - all through natural language commands backed by structured templates. Watch a stateful agent capture research, recall context from previous sessions, update its knowledge graph, and execute project workflows - without any model training or fine-tuning.

- Event context: AI Tinkerers Dhaka 2nd Meetup: Dhaka Builds with AI! — 2026-02-07 — Dhaka
- Public talk page: https://dhaka.aitinkerers.org/talks/rsvp_kSMaLnvvGGg

## Related Technologies

- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [AG-UI Protocol](https://aitinkerers.org/technologies/ag-ui-protocol) ([Markdown](https://aitinkerers.org/technologies/ag-ui-protocol.md)) — 2 public demos
- [AI agent](https://aitinkerers.org/technologies/ai-agent) ([Markdown](https://aitinkerers.org/technologies/ai-agent.md)) — 8 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [ARM](https://aitinkerers.org/technologies/arm) ([Markdown](https://aitinkerers.org/technologies/arm.md)) — 1 public demo
- [AVX2](https://aitinkerers.org/technologies/avx2) ([Markdown](https://aitinkerers.org/technologies/avx2.md)) — 1 public demo
- [axum](https://aitinkerers.org/technologies/axum) ([Markdown](https://aitinkerers.org/technologies/axum.md)) — 1 public demo
- [Bun](https://aitinkerers.org/technologies/bun) ([Markdown](https://aitinkerers.org/technologies/bun.md)) — 19 public demos
- [bun:sqlite](https://aitinkerers.org/technologies/bun-sqlite) ([Markdown](https://aitinkerers.org/technologies/bun-sqlite.md)) — 1 public demo
- [CRDT](https://aitinkerers.org/technologies/crdt) ([Markdown](https://aitinkerers.org/technologies/crdt.md)) — 1 public demo
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [GCC](https://aitinkerers.org/technologies/gcc) ([Markdown](https://aitinkerers.org/technologies/gcc.md)) — 1 public demo
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [Gemini CLI](https://aitinkerers.org/technologies/gemini-cli) ([Markdown](https://aitinkerers.org/technologies/gemini-cli.md)) — 16 public demos
- [LLVM](https://aitinkerers.org/technologies/llvm) ([Markdown](https://aitinkerers.org/technologies/llvm.md)) — 2 public demos
- [LLVM IR](https://aitinkerers.org/technologies/llvm-ir) ([Markdown](https://aitinkerers.org/technologies/llvm-ir.md)) — 1 public demo
- [Markdown](https://aitinkerers.org/technologies/markdown) ([Markdown](https://aitinkerers.org/technologies/markdown.md)) — 24 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos