Vollständiges Transkript anzeigen (2.053 Wörter)
Every week, developers release new open-source projects on GitHub, and this is our weekly GitHub project update video, covering the best of them. Top trending open-source GitHub projects this week. You’ll discover useful and trending developer tools, from local AI agents to self-hosted platforms. Without wasting time, let’s get started.
Before we jump into today’s project updates, here’s a quick announcement for everyone. We’ve launched a brand new YouTube channel called AI Agents Studio, dedicated entirely to AI agent projects, tutorials, and tools. So if you’re interested in staying up to date with the latest AI agent open-source projects, learning how to build your own agents, or exploring cutting-edge agent frameworks, make sure to check it out. Subscribe now to get weekly videos, in-depth guides, and real-time project breakdowns. The link is right there in the description. Don’t miss it. Alright, let’s get into today’s video!
Project number one, Hindsight: Long-term memory for AI agents that learns. Hindsight is open-source long-term memory for AI agents that learns. For coding agents, one package builds a per-repo memory bank from your git history and past sessions, injects it as the agent starts, and adds knowledge pages, SDKs, and a REST API, exposed, retain, recall, and reflect. With LiteLLM covering 100+ models. It integrates with Claude Code, Codex, Cursor, LangGraph, and CrewAI. A local daemon runs it all in one command. Install it and give your agent memory.
Project number two, NVIDIA Model Optimizer: Compress models for faster inference on NVIDIA GPUs. NVIDIA Model Optimizer, or ModelOpt, is an open-source library of model optimization techniques for compressing models and speeding up inference on NVIDIA GPUs. You feed it a PyTorch or ONNX model and stack techniques through Python APIs, quantization in FP8, INT8, INT4, and NVFP4, with post-training and quantization-aware training, plus sparsity, pruning, and distillation. The checkpoint deploys in TensorRT-LLM, TensorRT-VLLM, and SGLang, with HuggingFace export for transformers and diffusers. Install it with pip and optimize a model.
Project number three, OpenBao: Open-source secrets management, forked from HashiCorp Vault. OpenBao is an open-source secrets management platform for storing and distributing sensitive data, secrets, certificates, and keys under open governance, forked from HashiCorp Vault. It stores arbitrary key/value secrets encrypted before they touch disk, generates dynamic short-lived credentials on demand for AWS and SQL databases, and revokes them after their lease, and offers encryption as a service, so apps encrypt data without managing keys. It adds audit logs, PKI, and transit engines, and HSM/KMS backed keys. Deploy it and centralize your secrets.
Project number four, reverse-skill: Skill router for reverse engineering and authorized pentesting. reverse-skill is an open-source skill router that turns AI coding agents into assistants for reverse engineering, authorized penetration testing, and security research. When an agent hits an APK, a binary, front-end JS crypto, a CTF challenge, or a pentest task, this package routes it to the right methodology, then calls tools like Ghidra, Radare2, and Frida. Routing is a client-agnostic config, with a read-only case review layer for scope and findings. It works in Claude Code and Cursor. Install it and route your security work.
Project number five, Mobile Next: MCP server for iOS and Android automation. Mobile Next is an open-source MCP server for mobile automation and scraping across iOS and Android emulators, simulators, and real devices through one platform-agnostic API. It’s accessibility first, and an agent drives apps from the native accessibility tree, with no vision model, falling back to screenshots and coordinates only when needed. An LLM can automate user journeys, fill forms, and extract data from the screen. It works with Claude Code, Codex, Gemini, GitHub Copilot, Antigravity — or any MCP-compatible client. Install it and automate your app.
Project number six, Weknora: Turn documents into RAG, agents, and auto-wiki. Weknora is an open-source, LLM-powered knowledge platform from Tencent that turns documents into knowledge three ways: RAG-based Q&A for lookups, a React agent that orchestrates retrieval, MCP tools, and web search for multi-step tasks, and a wiki mode where agents distill documents into a self-maintaining, interlinked Markdown wiki with a knowledge graph. It ingests 10+ formats, auto-syncs from Feishu, Notion, and YuQue, works with 20+ LLM providers, and swaps vector databases. Self-host it with Docker and query your documents.
Project number seven, OpenCodeReview: AI code review CLI from Alibaba. OpenCodeReview is an open-source, AI-powered code review CLI from Alibaba. Its hybrid design pairs deterministic pipelines with an LLM agent. It reads your git diff, and the agent reads full files, searches the code base, and inspects changes, then returns line-level comments. The multi-language rule set catches issues like null pointer bugs, thread safety, XSS, and SQL injection, and it can auto-apply fixes. It works with OpenAI and Anthropic, with plugins for Claude Code and Codex. Install it and review your code.
Project number eight, God’s Eye View: Live open-source spatial intelligence on a 3D globe. God’s Eye View is an open-source, browser-based spatial intelligence console, a spy satellite simulator with real data. On a 3D globe, it layers live aircraft, ships, satellites, wildfires, and CCTV, so you move between a global view and a single object. You ride a tracked flight, lock onto anything to see its trail, and hand off to the nearest camera. It runs locally on public data, and by design it tracks assets and systems, not people. Build it and watch the world.
Project number nine, Magnitude: Private, offline AI agent with local models built in. Magnitude is an open-source AI agent that runs on local models, with its inference engine, so it’s private and offline, with no token costs or API keys. It profiles your hardware, recommends the models your machine can run, then downloads, configures, and tunes them. Its Rust engine, built on llama.cpp, calculates memory before loading and keeps parallel agents responsive. It uses your shell and edits files, and skills add Excel, PowerPoint, PDFs, and Chrome. Install it and run agents locally.
Project number 10, vphone-cli: Run a virtual iPhone on Apple Silicon. vphone-cli is an open-source command-line tool for creating and running a virtual iPhone on an Apple Silicon Mac. It uses Apple’s Virtualization.framework and research VM infrastructure, and a bundle handles firmware preparation, restore, and VM control. You point it at iPhone and CloudOS firmware, and it prepares, patches, restores, and boots the VM. The touch-enabled window supports file transfer, IPA install, screen recording, location, and an optional guest API. It ships an optional Launchpad GUI. Build it and boot a virtual iPhone.
Project number 11, DeskcommCRM: Self-hosted AI sales CRM for selling by chat. DeskcommCRM is an open-source, self-hosted CRM for businesses that sell by chat, an alternative to Kommo, Octadesk and Intercom. It combines a sales pipeline with AI agents and WhatsApp through WHA, so leads flow from chat and forms. The AI replies and books appointments, and a human can take over to stop the bot. It’s MCP ready and multi-tenant, with automations, scheduling, Google Calendar sync, and LGPD compliance. One command installs the stack on a VPS. Deploy it and sell by chat.
Project number 12, Soup: Fine-tune an 8B model on a 4 GB laptop. Soup is an open-source tool that fine-tunes LLMs from a YAML file. One config, one command, no SSH. Its layer streaming keeps the frozen base out of VRAM, and feeds the GPU one decoder layer at a time, so an 8B model fine-tunes on a 4 GB laptop card. It auto-handles batching and quantization, ships templates for chat, code, reasoning, vision, and preference tuning, and lets you chat with, merge and export to GGUF. Install it and fine-tune from one file.
Project number 13, Compositor: Free, open-source Photoshop alternative for Mac. Compositor is a free, open-source image editor for Mac, a Photoshop alternative for compositing and post-processing. It gives layers and folders with Photoshop’s full set of blend modes, layer masks, adjustment layers like curves, levels, and gradient map, and GPU-rendered layer effects like drop shadow, editable anytime. Moves, scales, and rotations stay non-destructive, and it imports PSD files with blend modes intact. AI agents can build projects too. A .comp is a folder of PNG layers plus a manifest. Download it and start compositing.
Project number 14, Search: A small, fast, minimal WebKit browser for macOS. Search is a fast, open-source WebKit browser for macOS, with no toolbar, start page, or account. Just tabs and the page. One field does it all. Type in an address and go, or words to search, completing from your history and sending nothing until return. Because it uses WebKit, the engine in every Mac, the app is 3MB and opens instantly, with no chromium in memory. It keeps passwords in the keychain and runs Chrome extensions. Download it and browse quietly.
Project number 15, qm: Multiplayer agent harness for a whole company. QM is an open-source multiplayer AI agent harness, open-source by Y Combinator and used internally at YC. Built for a company. It gives each employee their isolated workspace, scoped memory, files, credentials, crons, and a durable sandbox, while people collaborate with the agent in Slack channels and projects. Pi, OpenCode, Codex, and Claude Code all drive the same core, so you pick your harness and model. Security postures range from per-call approval to screen d’autonomy. It’s early, deploy it to your cloud.
Project number 16, herdr: The always-running terminal runtime for coding agents. Herd is an open-source multiplexer, the runtime your coding agents live on. It’s a background server owning their terminals, so agents survive a closed lid, dropped network, or restart, reattach from any terminal or over SSH. Every pane is marked working, blocked, or idle, so you never hunt for the stuck one. Agents drive it through a CLI and socket API, and it runs what you run, Claude Code, Codex, Cursor, and more. One rust binary. Install it and herd your agents.
Project number 17, OpenMuse: Personal agent with a browser, terminal, and files. OpenMuse is an open-source personal agent with a browser, terminal, and files, from CopilotKit. You ask for an outcome, follow the plan, review actions, and come back to the result. It runs a server and workers, giving the agent a computer, Chromium plus a Linux workspace, so it browses pages, runs commands, and handles files. Take over its browser or terminal anytime. It speaks AGUI, so you can swap the agent harness. It’s a template for iOS, Android, web, build your agent.
Project number 18, Open Glean: Self-hostable AI knowledge workspace over Hydra DB. Open Glean is an open-source AI workspace for knowledge work, built over Hydra DB, an Open Glean alternative. Ask a question across your memories, files, and connected apps, and it retrieves context, streams an answer with inline citations, a sources panel, and optional web search. A deep research mode plans a DAG of sub-questions, runs them against Hydra in parallel, writes a finding per branch, dedupes sources into one numbered citation list, then writes the answer. A timeline shows the plan and live progress. You bring your own OpenAI-compatible model, deploy it and ask your knowledge.
Project number 19, BongoCat: Desktop Bongo Cat that plays along as you type. BongoCat is an open-source desktop pet, the Bongo Cat overlay that plays along with your keyboard and mouse, reacting as you type and click. It’s a native app built in CC++ with SDL3 and OpenGL and stays lightweight. Input is read locally only, to drive animations and shortcuts. It never records or uploads keystrokes, and there are no ads, analytics, or tracking. It supports live 2D models and runs on Windows, with macOS and Linux in testing. Download it and boop.
Project number 20, mini-AGI: Continual-learning model trained from scratch on 8 GB. mini-AGI is an open-source continual-learning byte-level language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. It assembles its own architecture and stores weights as files on disk, paging them onto the card as it needs them, so its size is bounded by free disk space, not VRAM. It grows new capacity while training when it runs short, prunes what nothing asks for, and reads through exactly the same code path it serves on. It’s an experiment. Clone it and watch it learn.
Thanks for watching. See you in the next update.
Video
Video
Video
Video
