Show HN: Build Web Automations via Demonstration
Hacker News (score: 10)Description
We’ve been building browser agents for a while. In production, we kept converging on the same pattern: deterministic scripts for the happy path, agents only for edge cases. So we built Demonstrate Mode.
The idea is simple: You perform your workflow once in a remote browser. Notte records the interactions and generates deterministic automation code.
How it works: - Record clicks, inputs, navigations in a cloud browser - Compile them into deterministic code (no LLM at runtime) - Run and deploy on managed browser infrastructure
Closest analog is Playwright codegen but: - Infrastructure is handled (remote browsers, proxies, auth state) - Code runs in a deployable runtime with logs, retries, and optional agent fallback
Agents are great for prototyping and dynamic steps, but for production we usually want versioned code and predictable cost/behavior. Happy to dive into implementation details in the comments.
Demo: https://www.loom.com/share/f83cb83ecd5e48188dd9741724cde49a
-- Andrea & Lucas, Notte Founders
More from Hacker
Show HN: Daily-updated database of malicious browser extensions
Show HN: Daily-updated database of malicious browser extensions Hey HN, I built an automated system that tracks malicious Chrome/Edge extensions daily.<p>The database updates automatically by monitoring chrome-stats for removed extensions and scanning security blogs. Currently tracking 1000+ known malicious extensions with extension IDs, names, and dates.<p>I'm working on detection tools (GUI + CLI) to scan locally installed extensions against this database, but wanted to share the raw data first since maintained threat intelligence lists like this are hard to find.<p>The automation runs 24/7 and pushes updates to GitHub. Free to use for research, integration into security tools, or whatever you need.<p>Happy to answer questions about the scraping approach or data collection methods.
Rewrote our Python API gateway in Go and nobody cares
Rewrote our Python API gateway in Go and nobody cares
Show HN: Minikv – Distributed key-value and object store in Rust (Raft, S3 API)
Show HN: Minikv – Distributed key-value and object store in Rust (Raft, S3 API) Hi HN,<p>I’m releasing minikv, a distributed key-value and object store in Rust.<p>What is minikv? minikv is an open-source, distributed storage engine built for learning, experimentation, and self-hosted setups. It combines a strongly-consistent key-value database (Raft), S3-compatible object storage, and basic multi-tenancy. I started minikv as a learning project about distributed systems, and it grew into something production-ready and fun to extend.<p>Features/highlights:<p>- Raft consensus with automatic failover and sharding - S3-compatible HTTP API (plus REST/gRPC APIs) - Pluggable storage backends: in-memory, RocksDB, Sled - Multi-tenant: per-tenant namespaces, role-based access, quotas, and audit - Metrics (Prometheus), TLS, JWT-based API keys - Easy to deploy (single binary, works with Docker/Kubernetes)<p>Quick demo (single node):<p>git clone <a href="https://github.com/whispem/minikv.git" rel="nofollow">https://github.com/whispem/minikv.git</a> cd minikv cargo run --release -- --config config.example.toml curl localhost:8080/health/ready # S3 upload + read curl -X PUT localhost:8080/s3/mybucket/hello -d "hi HN" curl localhost:8080/s3/mybucket/hello<p>Docs, cluster setup, and architecture details are in the repo. I’d love to hear feedback, questions, ideas, or your stories running distributed infra in Rust!<p>Repo: <a href="https://github.com/whispem/minikv" rel="nofollow">https://github.com/whispem/minikv</a> Crate: <a href="https://crates.io/crates/minikv" rel="nofollow">https://crates.io/crates/minikv</a>
CLI's completion should know what options you've typed
CLI's completion should know what options you've typed
No other tools from this source yet.