HI version is available. Content is displayed in original English for accuracy.
The bet: WASM is a hard sandbox for free. When you generate tools with an LLM (or write them by hand), the studio AST-validates the source, registers it lazily, and JIT-compiles into Pyodide on first call. SQL tools run in DuckDB-WASM in a Web Worker. The built-in RAG uses Xenova/all-MiniLM-L6-v2 via Transformers.js for on-device embeddings. Nothing leaves the browser; close the tab and the stack is gone. The WASM boundary is what makes it safe to execute LLM-generated code locally — no Docker, no per-tenant container, no server.
Above the tool layer sits an agentic system with 10 orchestration strategies:
- Supervisor (router → 1 expert) - Mixture of Experts (parallel + synthesizer) - Sequential Pipeline - Plan & Execute (planner decomposes, workers execute) - Swarm (peer handoffs) - Debate (contestants + judge) - Reflection (actor + critic loop) - Hierarchical (manager delegates via ask_<persona> tools) - Round-Robin (panel + moderator) - Map-Reduce (splitter → parallel → aggregator)
You build a team visually: drag tool chips onto persona nodes on a service graph, pick a strategy, and the topology reshapes to match. Each persona auto-registers as an MCP tool (ask_<name>), plus an agent_chat(query, strategy?) meta tool. A bundled Node bridge speaks stdio to Claude Desktop and WebSocket to your tab — your browser becomes an MCP server.
When you're done, Export gives you a real Python MCP server: server.py, agentic.py, tools/*.py, Dockerfile, requirements.txt, .env.example. The exported agentic.py is a faithful Python port of the same orchestration logic running in the browser, so the deployable artifact behaves identically to the prototype.
Also shipped: Project Packs. Export the whole project as a single .agentpack.json. Auto-detects required external services (OpenAI, GitHub, Stripe, Anthropic, Slack, Notion, Linear, etc.) by scanning tool source for os.environ.get(...) and cross-referencing against the network allowlist. Recipients get an import wizard that prompts for credentials. Manifests are reviewable, sharable, and never carry secrets.
Some things I'm honestly uncertain about:
- 10 strategies might be too many. My guess is most users only need Supervisor, Mixture of Experts, and Debate. Open to data on which ones actually pull weight. - Browser cold-starts (Pyodide warm-up on first load) are a real UX hit despite aggressive caching. - bridge.js is the only non-browser piece. A hosted variant is the obvious next step.
Built with Pyodide, DuckDB-WASM, Transformers.js, OpenAI Chat Completions (or a local Qwen 1.5 0.5B running in-browser via Transformers for fully offline mode). ~5K lines of HTML/CSS/JS in one file.
Genuinely curious whether running this much LLM-generated code in a browser tab feels reasonable to you, or quietly terrifying.
Discussion (3 Comments)Read Original on HackerNews
The WASM boundary as a security primitive is underappreciated most people reach for containers without asking whether the threat model actually requires a persistent process. On the 10 strategies question: Supervisor and Mixture of Experts will cover 80% of real workloads in my experience, with Debate and Reflection worth keeping as the next tier since Debate surfaces assumptions single-agent pipelines miss and Reflection catches compounding errors cheaply. The part I would stress test is the export-to-Python parity keeping browser prototype behavior identical to the deployed artifact is a hard problem, and curious how you are handling edge cases where Pyodide’s stdlib coverage diverges from CPython.