3GitHub Trending (AI/LLM filtered)·
Microsoft open-sources AI-Engineering-Coach on GitHub
Microsoft has published AI-Engineering-Coach, a TypeScript repository on GitHub aimed at improving agentic engineering practices. The project has accumulated 3,378 stars with 79 added today, suggesting moderate community traction. Minimal description is available, but the Microsoft provenance and agentic focus make it worth indexing.
Related guides (2)
Related events (8)
Microsoft agent-framework: open-source library for building and orchestrating AI agents
Microsoft has published an open-source framework on GitHub for building, orchestrating, and deploying AI agents and multi-agent workflows, with support for both Python and .NET. The repository has accumulated 11,061 stars. It represents Microsoft's entry into the agent harness tooling space alongside existing frameworks like LangChain and AutoGen.
Microsoft 'skills' repo: MCP servers and agent grounding primitives for coding agents
Microsoft has published an open-source TypeScript repository called 'skills' that provides MCP servers, custom agents, and an Agents.md specification to ground coding agents within SDKs. The project appears to be infrastructure for standardizing how coding agents discover and invoke capabilities. With 2,656 stars and modest daily growth, it is an early-stage but notable contribution to the agent tooling ecosystem from a major lab.
danielmiessler/Personal_AI_Infrastructure: agentic AI infrastructure framework in TypeScript
Daniel Miessler's Personal_AI_Infrastructure is a TypeScript project on GitHub framed as agentic AI infrastructure for augmenting human capabilities, currently trending with ~14,925 stars and 63 new stars today. The repository appears to be a personal AI agent harness or orchestration layer. Limited detail is available from the trending listing alone, but the star count indicates meaningful community traction.
Microsoft Build: Seven in-house AI models, GitHub Copilot desktop agent manager, and Web IQ search API for agents
Microsoft announced seven new AI models trained from scratch (not distilled from OpenAI), including the flagship MAI-Thinking-1 reasoning model and MAI-Transcribe-1.5, plus a 'Frontier Tuning' reinforcement learning approach for enterprise workflow training. GitHub released a desktop Copilot app designed to manage multiple parallel AI agents with isolated git worktrees and bidirectional canvases. Microsoft also launched Web IQ, an agent-native Bing-powered grounding API already powering search in Copilot and ChatGPT, running 2.5x faster than alternatives with lower token costs. The roundup also covers Nous Research's Hermes Desktop cross-platform agent app, Alibaba's Qwen3.7-Plus multimodal model, and OpenAI's role-specific Codex plugins.
Sim Studio: open-source AI agent orchestration platform gains traction on GitHub
Sim Studio is an open-source TypeScript project for building, deploying, and orchestrating AI agents, positioning itself as a central intelligence layer for AI workflows. The repository has accumulated 29,089 stars with modest daily growth (+24). It represents a growing category of open-source agent harness tools competing with LangChain, n8n, and similar frameworks.
Microsoft Agent Governance Toolkit: Policy Enforcement and Zero-Trust Security for Autonomous AI Agents
Microsoft has published an open-source Agent Governance Toolkit on GitHub covering policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. The toolkit claims full coverage of the OWASP Agentic Top 10 security risks. It has accumulated 1,828 stars with 113 added today, indicating active community interest. This positions Microsoft as a contributor to emerging standards for safe agentic AI deployment.
Empirical study of agentic coding tool adoption across 2,361 GitHub repositories
Researchers analyzed 25,264 agentic pull requests from 2,361 popular GitHub repositories to characterize how agentic coding tools are adopted and managed at the project level. Key findings: median repos generate only 1-2 agentic PRs per three-month period, small projects (1-5 contributors) show higher participation ratios than larger ones, and human oversight is dominated by a single-reviewer model. The study provides early empirical grounding for understanding how open-source projects are integrating AI coding agents into their workflows.
RedPlanetHQ/core: Personal AI OS framework in TypeScript
RedPlanetHQ has published an open-source TypeScript project called 'core' on GitHub, described as a 'Personal AI OS.' The repository has accumulated 1,823 stars with 32 added today, indicating moderate community traction. The project appears to be an agent orchestration or personal AI management framework, though details are sparse from the available metadata.