localgpt

LocalGPT Gen is a Bevy-based tool where an AI agent builds explorable 3D worlds — geometry, behaviors (orbit, spin, path following), and spatial audio — then saves the entire world as a skill directory that other agents can load and remix. The skill format is a folder with a SKILL.md, a world.ron manifest preserving parametric shapes, and can have glTF export. Agents treat these the same as any other skill in their workspace. Inspired by blender-mcp and bevy_brp. The idea is to shrink the supply chain from intent to result — instead of prompt → code → build → deploy, it's prompt → explorable world. Example worlds: https://github.com/localgpt-app/localgpt-gen-workspace/tree/main/skills Video comparisons across different models: https://proofof.video Open source (Apache 2.0), written in Rust: https://github.com/loc

I couldn't get access to Project Genie 3, so I built a (very minified) version on top of LocalGPT, my local AI assistant in Rust. cargo install localgpt-gen — you describe a scene in natural language, the LLM generates it in Bevy. Early and rough, but it works: https://www.youtube.com/watch?v=n18qnSDmBK0 LocalGPT itself is a 38MB single-binary AI assistant with kernel-enforced shell sandboxing (Seatbelt/Landlock/seccomp) and HMAC-signed instruction files. localgpt-gen ships as a separate binary (>100MB) to keep the core small. Code: https://github.com/localgpt-app/localgpt Site: https://localgpt.app

See here: https://github.com/localgpt-app/localgpt/blob/main/src%2Fage...

See here: https://github.com/localgpt-app/localgpt/blob/main/src%2Fage...

git clone https://github.com/localgpt-app/localgpt.git cd localgpt/ edit cargo.toml and add "x11" to eframe cargo install --path ~/.cargo/bin Hey! is that Kai Lentit guy hiring?

It doesn't. It has to connect to SOME LLM provider, but that CAN also be local Ollama server (running instance). The choice ALWAYS need to be present since, depending on your use case, Ollama (local machine LLM) could be just right, or it could be completely unusable, in which case you can always switch to data center size LLMs. The ReadMe gives only a Antropic version example, but, judging by the source code [1], you can use other providers, including Ollama, just by changing the syntax of that one config file line. [1] https://github.com/localgpt-app/localgpt/blob/main/src%2Fage...

If local isn't configured then fallback to online providers: https://github.com/localgpt-app/localgpt/blob/main/src%2Fage...

> but I'm not really sure about calling it "local-first" as it's still reliant on an `ANTHROPIC_API_KEY`. See here: https://github.com/localgpt-app/localgpt/blob/main/src%2Fage...

I built LocalGPT over 4 nights as a Rust reimagining of the OpenClaw assistant pattern (markdown-based persistent memory, autonomous heartbeat tasks, skills system). It compiles to a single ~27MB binary — no Node.js, Docker, or Python required. Key features: - Persistent memory via markdown files (MEMORY, HEARTBEAT, SOUL markdown files) — compatible with OpenClaw's format - Full-text search (SQLite FTS5) + semantic search (local embeddings, no API key needed) - Autonomous heartbeat runner that checks tasks on a configurable interval - CLI + web interface + desktop GUI - Multi-provider: Anthropic, OpenAI, Ollama etc - Apache 2.0 Install: `cargo install localgpt` I use it daily as a knowledge accumulator, research assistant, and autonomous task runner for my side projects. The memory compounds — every session makes the next one better. GitH