Trending Repos

用 AI 大模型复刻聊天对象的本地对话 Agent：导入真实聊天记录，LLM 学习 TA 的语气、表情和回复节奏并以人物身份延续对话，支持语音、主动联系与长期记忆，数据全在本地。 | Clone anyone's texting style from real chat history: a local-first LLM agent that learns their tone, stickers and reply rhythm, then chats as them — voice, proactive messages, long-term memory, fully private.

独立、可自托管的 AI 动态心智状态引擎：驱动力、念头池、疲惫、睡眠与意图。

The free open source Grammarly alternative offline writing assistant assist with grammar, rewriting & tone entirely on your machine.

AI agent workflow platform — visual flow orchestration, drag-and-drop forms, knowledge base RAG, multi-model LLM, digital workers, Tauri desktop & DingTalk bot. Open source, self-hosted.

Self-hosted wishlist app. Share your list with anyone and let them claim gifts without giving away who bought what.

A small self-hosted guest lounge for your AI persona — friends chat via one-time links; you only ever see the AI-written visit summary. CC BY 4.0.

Introducing Muse Glimmer: open-weight 30B agentic multimodal model that runs on your device (Meta). Interactive local agent lab + guide. Apache 2.0 · on-device AI · function calling

Brevia · 言录(https://brevia.work): A minimal meeting recorder that stays on your device. Transcribe, distill with AI, remember—without the cloud. Clean interface, local storage, complete privacy. Zen-inspired design.

A modern Jellyfin dashboard for live sessions, user stats, recently added media, libraries, downloads, calendars, webhooks, and backups.

MCP Google AI searches using browser extension

我们的港湾

Config-driven homelab start page — sidebar of self-hosted services that load into an in-page pane, no build step, everything driven by YAML

Self-hosted, open-source mobile app analytics & ASO dashboard for Google Play Store and Apple App Store.

Open-source Starlink fleet monitoring — live telemetry, obstruction maps and alerting for every site. Includes a 40-dish gRPC simulator, so you can run the whole thing with no hardware.

AI hardware fit calculator for LLM, embedding, reranker, OCR and VLM workloads — VRAM, throughput, licensing and multi-GPU planning

An advanced, high-productivity prompt engineering suite for ComfyUI. This package introduces modal web interfaces (APIs) built directly into ComfyUI to seamlessly combine structured text lists, manual text blocks, and local LLM features via **Ollama** (both text enrichment and vision capabilities) without cluttering your node graph.

A video-call avatar frontend for your local LLM agent (Hermes/OpenClaw) — replaces the messenger chat and serves the agent's exact slash-command menu. Open-core engine: emotion, mood, voice, build-your-own-avatar pipeline. GPU-free · MIT.