I started out following Crafting Interpreters, but gradually branched off that until I had almost nothing left in common.
Tech stack: Rust, Cranelift (JIT compilation), LALRPOP (parser).
Original title: "A small programming language where everything is a value" (edited based on comments)
I was sick at home with the flu this weekend, and went on a bit of a Wikipedia deep dive about active American lighthouses. Searching around a bit, it was very hard to find a single source or interactive map of active beacons, and a description of what the "characteristic" meant. The Coast Guard maintains a list of active lights though, that they publish annually (https://www.navcen.uscg.gov/light-list-annual-publication). With some help from Claude Code, it wasn't hard to extract the lat/long and put together a small webapp that shows a map of these light stations and illustrates their characteristic with an animated visualization..
Of course, this shouldn't be used as a navigational aid, merely for informational purposes! Though having lived in Seattle and San Francisco I thought it was quite interesting.
The idea started as a pretty simple question: text chatbots are everywhere, but they rarely feel present. I wanted something closer to a call, where the character actually reacts in real time (voice, timing, expressions), not just “type, wait, reply”.
Beni is basically:
A Live2D avatar that animates during the call (expressions + motion driven by the conversation)
Real-time voice conversation (streaming response, not “wait 10 seconds then speak”)
Long-term memory so the character can keep context across sessions
The hardest part wasn’t generating text, it was making the whole loop feel synchronized: mic input, model response, TTS audio, and Live2D animation all need to line up or it feels broken immediately. I ended up spending more time on state management, latency and buffering than on prompts.
Some implementation details (happy to share more if anyone’s curious):
Browser-based real-time calling, with audio streaming and client-side playback control
Live2D rendering on the front end, with animation hooks tied to speech / state
A memory layer that stores lightweight user facts/preferences and conversation summaries to keep continuity
Current limitation: sign-in is required today (to persist memory and prevent abuse). I’m adding a guest mode soon for faster try-out and working on mobile view now.
What I’d love feedback on:
Does the “real-time call” loop feel responsive enough, or still too laggy?
Any ideas for better lip sync / expression timing on 2D/3D avatars in the browser?
Thanks, and I’ll be around in the comments.
It allows you to define different DNS-based rules that are resolved in a local daemon to IPs, then pushed to the eBPF filter to allow traffic. By doing it this way, we can still allow DNS-defined rules, but prevent contacting random IPs.
There's also no network performance penalty, since it's just DNS lookups and eBPF filters referencing memory.
It also means you don't have to tamper with the base image, which the agent could potentially manipulate to remove rules (unless you prevent root maybe).
It automatically manages the lifecycle of eBPF filters on cgroups and interfaces, so it works well for both containers and micro VMs (like Firecracker).
You implement a control plane, just like Envoy xDS, which you can manage the rules of each cgroup/interface. You can even manage DNS through the control plane to dynamically resolve records (which is helpful as a normal DNS server doesn't know which interface/cgroup a request might be coming from).
We specifically use this to allow our agents to only contact S3, pip, apt, and npm.
Maybe some of you will find it useful.
Happy to answer any questions.