Havuz

Autonomous multi-branch research lab. Branches compete for compute budget. The system converges on what works.

Open-source agentic AI Search Execution Platform. Track AI visibility, find opportunities, and let agents turn signals into prioritized acti

GPT Image 2.5 for e-commerce: prompt cookbook for listing photos, model try-on, product showcases, interaction scenes, and social commerce c

Full-featured DAW, DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Suno API, Chimera track fus

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs

TikZ for paper diagrams, without hand-writing TikZ — copyable icons, editable templates, and a Claude Code skill

Research artifacts from Hyra (/ˈhaɪ.rɑː/)

Experimental and pre-release tools for .NET MAUI

Skills Constitution — meta-rule governing all skill invocations across agent platforms

Sanitized Origin Pro MCP skill package with bilingual documentation

The why layer of repo-native project memory: the reasoning behind a codebase as Markdown in the repo, versioned by Git, for coding agents an

Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas

Runtime security for AI agents: discover agents, map their permissions, and enforce what they can do.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

KSoR (Knowledge System of Record) is an open-source SDK for building governed, authoritative knowledge systems for humans and AI agents. It

🚀 开源企业级多智能体平台与 ChatBI 数据洞察平台。支持多 Agent 协作、RAG 知识增强、物理数据源直连与安全沙箱执行、Redis 长期记忆引擎，并集成多模态 EmbedChat 挂件与全方位 Token 消耗审计看板，完整 RBAC权限控制和 Harness支持。

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Free, open-source memory for Claude Code. Your own database, no cloud, no subscription.

Parallel ai-agent sessions in one panel, with permission-aware tools, preflight conflict checks.

An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

协调探索、执行和独立评审，让复杂任务按明确职责并行推进，由主 Agent 统一验收。

122 个逆向工程 AI 技能：恶意软件分析 / 软件逆向 / 固件嵌入式 / 协议逆向 / 移动应用 / 脱壳反混淆 / 软件破解 / 漏洞挖掘 / 托管代码 / 取证情报 / CTF。

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

AI-agent skills for distributed-systems testing

Open agent skills and tool schemas for Superior Trade — build, backtest, and deploy trading strategies on Hyperliquid

AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts

台灣司法院判決 + 全國法規資料庫 MCP server · Query Taiwan legal data from any MCP AI agent

Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer ins

[EMNLP '26] Dependency-Aware Structural Retrieval for Massive Agent Skills

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Clau

Automatically resume Claude Code, Codex CLI, Grok, Qwen Code, Kimi CLI, OpenCode, and Antigravity sessions when 5-hour or weekly usage limit

10-part module to build AI-native apps. From data analysis to multi-agent model harness. For curious learners and serious AI builders.

Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compr

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimizati

Markdown-first orchestration for 71 specialists across Codex, Claude, Gemini, and Grok. Chrono coordinates scoped tasks in isolated git work

One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local tools, and MCP.

Korean DART + SEC EDGAR filings as structured Python data for company analysis

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

A repository for skills that are essential to my daily work

Use your own DeepSeek web account through OpenAI & Anthropic-compatible APIs. FastAPI reverse proxy with tool calling, vision & streaming.

Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil

Searchable football data provider documentation for AI coding agents. Like Context7 for football data.

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

Ailin¹ is an open-source collective intelligence engine where tens of thousands of AI models collaborate through dozens of coordination stra

Multi-agent autonomous framework — let your AI work while you sleep 🌙

Mirror the official Claude desktop app installers (macOS universal DMG, Windows x64/arm64 MSIX) into GitHub Releases + Cloudflare R2 short l

Open-source AI interview platform for voice, chat & video

Reusable AI prompt and project brief system for cinematic scroll-driven 2.5D websites.