Agent orchestration, security auditing and local AI tools dominate this week's trends

stablyai/orca

An orchestrator that runs Codex, Claude Code, OpenCode and Pi side-by-side — Orca lets you run multiple coding agents (Codex, ClaudeCode, OpenCode, Pi) in parallel, each in its own git worktree, tracked from one desktop app. A mobile companion app notifies you and lets you steer agents remotely. Built for builders juggling several AI coding agents with their own subscriptions.

Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

akitaonrails/ai-memory

Shared memory that lets coding agents swap places mid-task — ai-memory is a Rust tool giving AI coding agents a shared, cross-vendor memory. It lets you quit one harness (Claude Code, Codex, Cursor, Gemini CLI, and 20+ others) and resume in another with full context on progress, failures, and open questions, plus a portable profile of your work habits across projects.

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

ruvnet/ruflo

A meta-harness evolving Claude Flow's multi-agent swarm tooling — Ruflo is an agent meta-harness for Claude Code and Codex, tracing its lineage to the original Claude Flow project. It adds adaptive memory, self-learning behavior, federation, and vector RAG support, installable as Claude Code plugins for developers building multi-agent swarms and conversational AI systems.

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

makecindy/cindy

A local AI agent that combines harnesses like Claude Code and Codex — Cindy is an open-source desktop/mobile AI agent that runs locally on your own files and logged-in apps, mixing multiple harnesses (Claude Code, Codex, more coming) and models that can switch mid-task. It drives your browser, computer and phone, with continuous memory and skills, and is Apache-2.0 licensed.

Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。

anthropics/claude-plugins-official

Anthropic's own marketplace for Claude Code plugins — This is Anthropic's official, curated directory of Claude Code plugins, split into internal (Anthropic-built) and external (partner/community) entries. Plugins install directly via Claude Code's `/plugin install` command, giving users and third-party developers a vetted, standardized way to extend Claude Code with commands, agents, skills, and MCP servers.

Official, Anthropic-managed directory of high quality Claude Code Plugins.

cloudflare/security-audit-skill

Turning coding agents into structured, self-verifying security auditors — This skill orchestrates isolated agents through a six-phase security audit: recon, coverage-led hunting, candidate validation, structured findings, independent verification, and reporting. It's the single-repo seed behind Cloudflare's larger vulnerability discovery harness, useful for teams wanting reproducible, machine-readable audit trails rather than one-shot AI scans.

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

NVIDIA/OpenShell

NVIDIA's policy-enforced sandbox runtime for AI agent fleets — OpenShell confines autonomous agents with kernel-level sandboxing and policy checks on file, syscall, and network access, injecting credentials only for approved endpoints. Formal verification flags risky policy changes before approval. Version 0.1.x adds new isolation primitives, an expanded extension surface, and new APIs.

OpenShell is the safe, private runtime for autonomous AI agents.

DietrichGebert/ponytail

A YAGNI prompt pack that makes AI coding agents write less code — Ponytail installs a skillset/ruleset that pushes AI agents like Claude Code and Cursor toward minimal, boring solutions instead of over-engineered ones. It targets developers using agentic coding tools who want fewer unnecessary abstractions, and claims compatibility with around 20 different agents.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

pbakaus/impeccable

A design skill set to stop AI coding agents from building the same SaaS look — Impeccable extends Anthropic's frontend-design skill with 24 commands, 61 deterministic detector rules, and live browser iteration, aimed at making AI-generated frontends look less templated. It's for developers using AI coding tools who want shared design vocabulary and automated checks instead of repetitive gradients, card-in-card layouts, and generic icon tiles.

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

Nutlope/hallmark

A skill that catches the telltale signs of AI-made web pages — Hallmark is a design skill for Claude Code, Codex, Cursor and OpenCode that lints generated pages in a real browser against common AI-slop tells, like eyebrow headings or empty hero sections. V2 adds 48 material-based themes, job-driven layouts, custom prompts, and redesign/audit commands for existing pages or live URLs.

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

Graphify-Labs/graphify

Deterministic knowledge graphs for your codebase, no vectors needed — Graphify builds a queryable knowledge graph from code, docs, SQL schemas, configs, and PDFs using local deterministic AST parsing with tree-sitter, not embeddings. It ships as a /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI, with every graph edge explained for AI agents doing code search and analysis.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

debpalash/VoiceStudio

A fully local, open-source voice studio covering 646 languages — VoiceStudio bundles voice cloning, voice design, dubbing, dictation, transcription and audiobook creation into one local-first tool, positioned as an open-source ElevenLabs alternative. It runs on CUDA/MLX, exposes a local API and MCP for agents, and supports watch folders and reusable recipes for automated workflows.

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Kruk2/jasna

GPU-powered mosaic removal for videos with a free app and CLI — Jasna detects and restores mosaics in videos and images while leaving the rest of the frame untouched. It offers a free BasicVSR++ model plus a slower, more detailed LTX model for supporters, a Segment Editor for selective restoration, VR180 support, and a live preview Video Player—aimed at users with NVIDIA or experimental AMD GPUs.

Video restoration tool

shiyu-coder/Kronos

An open foundation model trained on financial K-line data — Kronos is pitched as the first open-source foundation model built specifically for financial candlestick data, pretrained across 45+ global exchanges. It ships pretrained weights on Hugging Face plus a live demo, aimed at quants and researchers who want a reusable base model for market time-series tasks instead of training from scratch.

Kronos: A Foundation Model for the Language of Financial Markets

Renhuai123/ziwei-doushu

An open-source Zi Wei Dou Shu engine with a massive interpretation dataset — A Chinese astrology (Zi Wei Dou Shu) calculation engine built on Ni Haixia's teaching system, pairing a full chart algorithm with a v4.0 dataset: 674,976 charts × 13 dimensions, ~8.77 million interpretation segments, 56.6GB uncompressed. Useful for researchers, developers, or enthusiasts building divination apps or studying traditional Chinese fortune-telling data at scale.

紫微斗数开源排盘引擎 — 基于倪海厦《天纪》体系，含完整排盘算法、四化系统、格局知识库、古籍原文数据

withmarbleapp/os-taxonomy

An open prerequisite graph mapping what kids learn, K-6 — Marble's open dataset breaks primary-school learning into 1,591 micro-topics linked by 3,225 prerequisite edges, forming a directed graph across 8 subjects. Each topic ties to curriculum standards (NGSS, Common Core, UK) and includes mastery evidence; useful for edtech builders, researchers, or curriculum designers needing structured, connected learning data instead of flat standards lists.