* [pooled v1.0.0](https://github.com/Nehanth/pooled) – Browser-based peer-to-peer LLM inference that pools model layers across devices in a room for fast chat and in-tab coding agents.

* [overtchat mobile-v1.13.0](https://github.com/yoloyash/overtchat) – Lightweight self-hosted chat client focused on fast startup, low resource use, and BYO API keys or local models, with optional web search and mobile support.

* [ReadyLLM v0.3.0](https://github.com/htobty/ReadyLLM) – Visual interface for deploying, monitoring, and tuning local LLMs, with hardware-aware parameter search and ComfyUI-based image and video generation.

* [pi-task v0.42.16](https://github.com/mjasnikovs/pi-task) – Deterministic spec-orchestration for local models, running fixed refine→research→grill→compose→critique pipeline with crash-safe persisted checkpoints and bundled web/docs/fetch worker tools.

* [Off Grid AI v0.0.51](https://github.com/off-grid-ai/OGAD) – Local-first AI runtime with a studio and an OpenAI-compatible gateway, running open multimodal models entirely on-device with an optional always-on assistant layer.

* [codehamr 2026-09-19](https://github.com/codehamr/codehamr) – Minimal local-first terminal coding agent that uses local LLMs or OpenAI-compatible endpoints, runs a single tool loop, edits project files, and verifies changes by running project checks.