AI 开源项目

Real-time audio translation, captures system audio + mic, runs ASR (Whisper/SenseVoice), translates via LLM API with streaming display. Perfect for VTubers, livestreamers, and watching foreign content. Windows 实时音频翻译，ASR 语音识别后 LLM 流式翻译显示，适合 VTuber、主播和外语视频观看。

Openclaw记忆插件Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

RDNA-native LLM inference engine in Rust.

Open-source Grok Bot alternative. Choose your own model and sandbox.

Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more

Free, two-way Figma MCP server. Turn designs into framework-aware code, and push code back to the canvas. Works with Claude Code, Cursor, Codex, and any MCP client.

Unified Play Integrity and root hiding stack for Android

DeepSeek Harness (dsh) Windows / Linux desktop client - bundled Node.js + dsh CLI, one-click launch, 10 built-in UI skins. EAC: Embracing All Creation 揽尽万象

An in-the-wild benchmark for AI agents in the OpenClaw Environment.

暂无项目简介。

Learn agent fundamentals from scratch in one day (about 9 hours)! I wrote this tutorial to show that agents are actually very simple. 零基础一天 （9小时）学完agent！写这个教程就是想告诉大家，Agent其实非常简单！

FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 285 commands, 244 MCP tools, change-safety gates, audit evidence, zero API keys.

让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

Open-source, local-first video editor where creators and AI agents edit the same real timeline.

Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.

TUI and CLI for browsing AI models, benchmarks, coding agents, and statuses for AI providers.

Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)

Desktop app for DeepSeek Harness

Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.

KohakuTerrarium is a general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.