GitGenius daily developer trends - June 4, 2026
Published: 6/4/2026
This daily roundup highlights repository momentum from GitGenius analytics for June 4, 2026, using UTC daily deltas in stars and subscribers.
The scan reviewed 1875 repositories, with 1760 repos contributing star deltas and 1760 repos contributing subscriber deltas.
Repo of the day
NousResearch/hermes-agent led the day with +1899 stars to 180938 total stars and +8 subscribers to 709 total subscribers. Hermes Agent, developed by Nous Research, is a self-improving AI agent designed to grow with its user. Its primary function is to provide an intelligent and adaptable conversational interface, capable of learning from experience, improving its skills, and building a personalized understanding of the user over time. The agent is designed to be versatile, running on various infrastructures, from a $5 VPS to a GPU cluster or serverless environments, and accessible through multiple platforms.
A core feature of Hermes Agent is its built-in learning loop. This loop enables the agent to create new skills autonomously after complex tasks, refine these skills through ongoing use, and actively retain knowledge. It achieves this through a combination of agent-curated memory, periodic knowledge nudges, and a full-text search (FTS5) of past conversations, summarized by an LLM, for cross-session recall. This allows the agent to remember and leverage past interactions, making it more effective over time. Furthermore, Hermes Agent integrates with the agentskills.io open standard, promoting interoperability and skill sharing.
The agent offers a real terminal interface with features like multiline editing, slash-command autocomplete, conversation history, and streaming tool output. It also provides a messaging gateway, allowing users to interact with the agent through various platforms, including Telegram, Discord, Slack, WhatsApp, Signal, and CLI. This multi-platform support ensures that users can access and utilize the agent from their preferred communication channels.
Hermes Agent is designed to be highly customizable and adaptable. Users can choose from a wide range of Large Language Models (LLMs) from providers like Nous Portal, OpenRouter (with 200+ models), z.ai/GLM, Kimi/Moonshot, MiniMax, and OpenAI, or even their own custom endpoints. Switching between models is straightforward, requiring no code changes. The agent also supports scheduled automations, allowing users to set up tasks like daily reports, nightly backups, and weekly audits, all in natural language and running unattended.
Beyond its core conversational capabilities, Hermes Agent supports delegation and parallelization. It allows users to spawn isolated subagents for parallel workstreams and write Python scripts that call tools via RPC, streamlining multi-step pipelines. The agent is also designed with research in mind, offering features like batch trajectory generation and integration with Atropos RL environments.
Installation is simplified with a single-line command that handles all dependencies. The project provides comprehensive documentation, including quickstart guides, CLI usage instructions, configuration details, and guides for the messaging gateway, security, tools, skills, memory management, and more. The documentation is readily available at hermes-agent.nousresearch.com/docs.
For users migrating from OpenClaw, Hermes Agent offers a migration tool to import settings, memories, skills, and API keys. The project actively encourages contributions and provides detailed instructions for developers, including development setup, code style guidelines, and the PR process. A vibrant community is fostered through Discord, a Skills Hub, and issue and discussion forums on GitHub. The project is licensed under the MIT license, promoting open use and modification. In essence, Hermes Agent is a powerful, flexible, and evolving AI assistant designed to enhance user productivity and knowledge retention through its self-improving capabilities and versatile integration options.
Fastest rising repos
- NousResearch/hermes-agent - +1899 stars (180938 total), language: Python. The agent that grows with you
- colbymchenry/codegraph - +1583 stars (40847 total), language: TypeScript. Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
- affaan-m/ECC - +1511 stars (207179 total), language: JavaScript. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
- microsoft/markitdown - +1422 stars (144236 total), language: Python. Python tool for converting files and office documents to Markdown.
- mattpocock/skills - +1207 stars (117597 total), language: Shell. Skills for Real Engineers. Straight from my .claude directory.
Subscriber surge
- multica-ai/andrej-karpathy-skills - +13 subscribers (918 total), +874 stars. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
- NousResearch/hermes-agent - +8 subscribers (709 total), +1899 stars. The agent that grows with you
- obra/superpowers - +6 subscribers (828 total), +1015 stars. An agentic skills framework & software development methodology that works.
- lfnovo/open-notebook - +6 subscribers (124 total), +678 stars. An Open Source implementation of Notebook LM with more flexibility and features
- affaan-m/ECC - +5 subscribers (1041 total), +1511 stars. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Hidden gems
- calfonso/rusternetes - +3 stars to 432 total stars, 2 subscribers. kubernetes, reimplemented in Rust
- mannaandpoem/OpenManus - +2 stars to 486 total stars, 13 subscribers
- micytao/vllm-playground - +2 stars to 467 total stars, 5 subscribers. A modern web interface for managing and interacting with vLLM servers (www.github.com/vllm-project/vllm). Supports both GPU and CPU modes, with special optimizations for macOS Apple Silicon and enterprise deployment on OpenShift/Kubernetes.
- bradtraversy/macrozone - +2 stars to 119 total stars, 1 subscribers. React native crash course project. An app to track daily macros
- anysphere/gpt-4-for-code - +1 stars to 493 total stars, 14 subscribers. Some examples of GPT-4 for code!
Language movers
- python - +17714 stars across 325 repos. Example repos: NVIDIA/cutile-python, microsoft/agent-lightning, openai/gpt-oss
- typescript - +11864 stars across 224 repos. Example repos: nrwl/nx, amantus-ai/vibetunnel, QwenLM/qwen-code
- rust - +4290 stars across 74 repos. Example repos: BloopAI/vibe-kanban, farion1231/cc-switch, firecracker-microvm/firecracker
- shell - +3619 stars across 24 repos. Example repos: VoltAgent/awesome-claude-code-subagents, frankbria/ralph-claude-code, obra/superpowers
- javascript - +2575 stars across 52 repos. Example repos: facebook/react, micytao/vllm-playground, Piebald-AI/claude-code-system-prompts
Category spotlight
- machine learning - +7289 stars across 185 repos. Example repos: amantus-ai/vibetunnel, openai/gpt-oss, onnx/onnx
- ai - +5046 stars across 64 repos. Example repos: frankbria/ralph-claude-code, anthropics/skills, multica-ai/multica
- ai agents - +4707 stars across 36 repos. Example repos: microsoft/agent-lightning, NousResearch/hermes-agent, MemoriLabs/Memori
- automation - +4501 stars across 118 repos. Example repos: microsoft/agent-lightning, rest-assured/rest-assured, shiyu-coder/Kronos
- deep learning - +4175 stars across 116 repos. Example repos: NVIDIA/cutile-python, openai/gpt-oss, QwenLM/qwen-code
Maintainer watch
- microsoft - +2283 stars across 32 repos. Example repos: microsoft/terminal, microsoft/agent-lightning, microsoft/VibeVoice
- nousresearch - +1899 stars across 1 repos. Example repos: NousResearch/hermes-agent
- colbymchenry - +1583 stars across 1 repos. Example repos: colbymchenry/codegraph
- affaan-m - +1511 stars across 1 repos. Example repos: affaan-m/ECC
- anthropics - +1259 stars across 11 repos. Example repos: anthropics/skills, anthropics/claude-plugins-official, anthropics/knowledge-work-plugins
