I’ve been building Personal Jarvis as an open-source desktop agent that sits above the models and tools you already use.
Instead of being tied to one provider, it can work with local models, hosted models, existing AI subscriptions, MCP servers, skills and plugins. It also includes computer use, voice, persistent agents, memory, routines and coding-agent workflows.
The part I’m most interested in is the orchestration layer: Jarvis is not the model itself. It connects the model, tools, agents and desktop actions into one workspace.
If you want to watch demos, go to my YouTube channel. I don't make any money from this. This is completely free and open source. https://www.youtube.com/@PersonalJarvis
Hello, I'm Ruben. My vision was with personal Jarvis to build an AI voice agent, which drives coding agents, runs shell commands, operates your computer, connects anything that speaks MCP, dictates into any app, and remembers everything, and it can run fully on your own hardware. This project is built in Python
Two questions about the fork boundary. The snapshot is taken once when the process calls listen, so every later instance is a clone of the same frozen memory image, and anything seeded during init is identical across every clone in every region. That is exactly what the Linux vmgenid driver exists for, and it is why Lambda SnapStart had to ship explicit reseeding guidance. I could not find entropy, RNG or reseed anywhere in the runtime, performance or security docs, so is there a post-restore reseed hook, and does it fire before the first accept?
The other one is syzy. CRDT.md says eviction is operator-driven, that PRUNING.md is a design-stage contract and not yet code, and that a replica lagging beyond the hold window may transiently observe the departing duplicate, while the product headline offers scale to zero when idle, which mints offline replicas continuously. Who calls syzy_evict in the managed product?
These are both later-stage detail questions for when this project is further hardened for production workloads, but here's where each of these currently stands:
- Yes, there is a post-restore kernel reseed hook that happens after fork, and just before the trapped listen is continued. It doesn't use the vmgenid driver, it just calls the RNDRESEEDCRNG ioctl, so it would not be compatible with applications that depend on vmgenid notifications to reseed userspace PRNGs.
- In Syzy, the full pruning implementation is deferred for now; at the managed product's current small scale, it can simply eat the tiny overhead costs of un-collected garbage, while the user is only billed for the logical storage space consumed.
