GitHub 2026-03-13 Weekly Trending Projects

Persona-centric AI agent collection with production-ready Claude Code templates for rapid specialist assistants; license and maintenance transparency are lacking.

MiroFish is a multi-agent, long-memory simulation prediction platform that maps real-world seed data into high-fidelity digital worlds, enabling natural-language-driven scenario simulations and automated report generation for public opinion, policy and creative sandboxing, while requiring attention to licensing and operational risks.

A Google Cloud Vertex AI sample repository covering Gemini, RAG, vision and audio workflows—useful for learning and prototyping; verify license and maintenance before production use.

AIRI is a hybrid Web/local self-hosted virtual character platform focused on real-time voice, game interaction, and multi-platform deployment—suited for developers and creators seeking controllable, customizable virtual streamers and digital companions.

An AI-driven hedge-fund proof-of-concept for research and education that composes multiple investing-persona agents, backtesting, CLI and web UI, and configurable LLM/data integrations — enabling strategy prototyping and model evaluation while explicitly disallowing real-money trading; note it lacks a declared license and production-grade guarantees.

Hermes Agent is a server-deployable autonomous AI agent offering a terminal-first interface, multi-platform messaging gateway, persistent memory and skills hub, sandboxed terminals, and scheduling—suitable for long-running, auditable, and extensible automation in engineering and operations.

BettaFish is a modular multi-agent public-opinion analysis engine for enterprises and researchers that aggregates multi-source multimodal data and produces actionable reports via agent-forum collaboration; however, license, dependency and operational details must be clarified to reduce production risks.

An agent framework built for Qwen models that offers tool-calling, planning and memory features with multiple practical demos—suited for building multi-step, explainable LLM apps; verify license and community maintenance before production use.

notebooklm-py delivers full programmatic access to Google NotebookLM via async Python API and CLI for research and prototyping; it depends on undocumented APIs and has unclear licensing, so avoid production use.

Extensible super-agent runtime with skills, sandbox execution and memory.

BitNet is Microsoft's open-source inference framework that uses 1-bit (1.58-bit) representations and optimized kernels to reduce energy and accelerate large-model inference on CPU/GPU, enabling efficient edge and on-device deployments.

Modular Claude skills: docs, Python tools, and plug-and-play bundles for teams to quickly extend AI assistant capabilities.

Promptfoo is a developer-focused CLI and library for automated LLM evaluation and red-teaming, supporting local/private execution, multi-model comparisons, and CI integration to improve model reliability and security.

SEO Machine is a Claude Code–based end-to-end SEO writing and optimization workflow that combines research, writing, review, and performance data to produce brand-aligned long-form SEO content; however, license and maintenance activity should be confirmed before production use.

AReaL is presented as an asynchronous RL training platform for large reasoning and agent models, emphasizing scalability and high throughput; it suits research or engineering teams requiring large-scale RL and toolchain integration, but license absence and inconsistent repository metadata pose compliance and maintenance risks.