Havuz

A scheduled, agent-driven software factory. Keep a plain JSON backlog; Forgeo runs your coding agent (Claude Code, Codex, opencode) on each

The Kimi K3 and DeepSeek-V4-Flash-0731 architectures, reimplemented from scratch in pure Rust (zero dependencies) and verified 1:1 against t

One hotkey to ask any AI on Mac. Open-source menu bar assistant: press ⌥Space to ask with your own API key (OpenAI, Claude, any OpenAI-compa

Make AI writing sound like you, not like AI. Two Claude Code skills that audit text against your own voice and fix only what fails.

aiduMEI⚕爱嘟优忆思——aidu Memory Engine Insight · 智能体通用智慧引擎——Excellent memory system for all agents.

A CV website that answers questions about you — even when you're offline. Powered by Llama 3.3 via Cloudflare. Free forever.

Sách miễn phí tiếng Việt về vibe coding cho Tester, PM, BA — người làm IT không viết code. 20 chương, 3 phụ lục, 54 hình. Học cách chỉ đạo A

A personal substrate for agent packages that ship their own screens. One manifest declares the agent, its verbs, and its UI.

aiduPOP☤爱嘟泡波浪 (aidu-customized Feishu/Lark streaming card plugin for Hermes Agent)

TinyFish MCP server — web search, page fetching & extraction, browser automation and page monitoring for Claude, Cursor, VS Code and any MCP

The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/g

璇玑 Xuanji —— Go 单二进制 AI 网关，OpenAI / Anthropic 双协议汇聚。one-api / new-api / LiteLLM 轻量替代品，自动分流、负载、重试，成本优先路由，高可用不中断。

🐶 An LLM-powered local-service watchdog: probe → diagnose with LLM → 4 guardrails → fix → verify → self-heal. Learns from bugs it fixes. sys

MAC, doğal dildeki tasarım brief’lerinden düzenlenebilir CAD parçaları ve deneysel olarak çok parçalı assembly’ler üretir.

Neden yükseliyor · 59 günde 1006 yıldıza ulaşması, doğal dilden CAD üretimine yönelik ilgiyi ve görsel olarak etkileyici parça/assembly demolarını yansıtıyor. Ancak README, assembly örneklerinin seçilmiş çıktılar olduğunu ve ölçülmüş prompt başarı oranı sunmadığını belirtiyor; 28 günde 22 commit olsa da farklı yazar sayısının 1 olması benimseme ve sürdürülebilirlik kanıtını sınırlıyor.

An esoteric programming language built to break LLMs and coding agents.

Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком

Centrally manage AI-agent skills, tools, context, permissions, and identity across your entire org. Self-hosted, Git-backed and MCP-native.

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

将 Qoder 的 AI 服务转化为兼容 OpenAI/Claude/Codex 格式的 API，支持每日签到领 Credits、多账号管理、模型上下文展示

Agent Harness for long-running agents that remember, continue, and learn from real work.

Official Repo for "AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach"

The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability

A browser game to learn prompt engineering by playing — explore a world and solve challenges by writing prompts. Techniques from OpenAI, Ant

A fully transparent in-editor agentic harness for large language models inside Godot Engine. Connect to any LLM provider via API (or use you

A graph-native simulation engine for building composable engineering simulations and digital twins.

KVerus: Scalable and Resilient Formal Verification for Rust Code

CADPilot is an MCP server that lets AI clients (ClaudeCode, OpenCode, DSH, ZCode) pilot FreeCAD, building constrained sketches, parametric f

OpenRouter TypeScript harness for reproducible LLM benchmarks and evaluations.

一个本地ai聊天模型localaiAgentWithRAG，让你的本地数据不上传云端，可以自己加入所需要的记忆文件等等，修改角色形象，记忆对话，记忆库允许自己导入或者对话后自动记录

Annona — the sovereign execution kernel for AI agents. Decides where each step runs, enforces it, and records it.

Open-source agentic AI operating layer for hospital operations — multi-agent orchestration over FHIR-connected HIS data, built on LangGraph

企业自托管 AI Code Review Agent ，一键自动分析 GitLab MR 与 Push，并回填总评和行内 Discussion。

Run Claude Code agents on a schedule. They stay silent unless there's something worth telling you — a quiet day costs zero tokens.

AI Minecraft adventure map generator: story in, it generates a playable RPG dungeon datapack with quests. A Claude Code skill (LLM agent).

Evidence-backed structural validation of Kimi K3 UD-IQ1_M and UD-Q4_K_XL split GGUF releases using OMIV.

Hypit, AI agents kullanarak video düzenleme iş akışları oluşturup bunları SVML tabanlı bir sistemle videoya dönüştüren bir araçtır.

Neden yükseliyor · 60 günde 16.443 yıldız, son 28 günde 566 commit ve 15 farklı yazar güçlü ilgi ve geliştirme aktivitesine işaret ediyor. Video üretimi ile AI agents gündeminin kesişmesi dikkat çekmesini açıklayabilir; ancak README'deki “100M views” vaadi bir sonuç kanıtı değil.

Vibe AStock, A-share kısa vadeli piyasa takibi ve günlük değerlendirme iş akışını yerel bir web dashboard’unda birleştiren bir araştırma aracıdır.

Neden yükseliyor · Açıklama ve özellik kapsamı, kısa vadeli piyasa analizindeki somut bir iş akışını uçtan uca ele alıyor; 66 günlük yaşına karşı 644 yıldız ve son 28 günde 25 commit ile 4 farklı yazar da belirgin ilgi ve yakın dönem geliştirme faaliyeti gösteriyor. Yükselişin kesin nedeni verilerden anlaşılamaz.

GeoLook, markaların AI yanıtlarında ne sıklıkta göründüğünü ölçüp site denetiminden uygulanabilir işlere ve doğrulamaya uzanan self-hosted bir GEO iş akışı sunuyor.

Neden yükseliyor · 60 günde 731 yıldız, yeni GEO kategorisine yönelik belirgin ilgiye işaret ediyor; ancak yükselişin nedeni doğrulanamıyor. Son 28 günde commit ve farklı yazar olmaması, yıldız ilgisinin güncel geliştirme faaliyetiyle desteklenmediğini gösteriyor.

Benzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, contr

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, s

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Deterministic-first execution engine for agent workflows in Go: the LLM extracts at the edge, a deterministic state machine decides. Zero de

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

Run LLMs and Ollama Qwen across AMD XDNA1 NPU, CPU, and GPU on Ryzen AI Linux systems.

Claude Code skill that delegates implementation to GPT-6.1 (whatever is the latest) Sol via Codex CLI, Claude plans and reviews the diff, So

Verify the context you feed your AI agents, against the web or your own documents.

🚀 One API gateway for GPT, Claude, Gemini, DeepSeek and more. OpenAI-compatible API for developers.

Suijin is an open-source fully autonomous red teaming / web app pentesting framework for AI models. Powered by LangGraph, designed for bug b