Havuz

Agent-driven SAP/ABAP knowledge base engine that turns S/4HANA custom objects into citable Markdown/Obsidian context for humans and AI agent

这是一个ai infra、关于LLM的一切的的obsidian知识库 可以配合agent使用 持续更新中。

本地优先的 AI 求职工作台：采集与管理 BOSS 直聘岗位，基于真实经历匹配 JD、定制简历并准备面试，支持 MCP 接入 Claude Code、Codex 等 Agent。

Give text based LLMs in Claude Code working eyes using a local Ollama vision model. Screen capture, clipboard reading, and image file analys

A production GenAI architecture guide for Forward Deployed Engineer (FDE) and Applied AI interviews—RAG, agents, evals, security, and operat

KoutenDB: locality-aware NoSQL document/vector database built around rings and orbit-inspired retrieval

溪语 AI · 一个尽力像真人的开源 AI 陪伴框架（微信 + Node + SQLite + LLM）她心里悄悄喜欢你，但绝不用愧疚拴住你。

Request-level image lifecycle middleware for AI coding agents: keep current-turn images, downgrade historical ones to stable placeholders.

AI Powered Reverse Engineering Tool

The web scraping API that turns any URL into clean data.

Agent Orchestrator App

Hi Code — 本地优先的桌面编码 Agent 工作台 · a local-first desktop coding agent workbench for any OpenAI-compatible model

Model Shell Protocol: an application-owned command runtime that gives AI agents OS-like workspace semantics.

Kaiwa (会話) — open-source Japanese conversation tutor that runs entirely on your own computer. Chat, voice calls, roleplay, corrections & SRS

Konnect, LLM’lerin KiCad 10 projelerinde şema ve PCB düzenlemeleri yapmasını sağlayan bir MCP sunucusu ve native plugin’idir.

Neden yükseliyor · 84 günlük bir repo için 798 yıldızın yanı sıra son 28 günde 291 commit ve 5 farklı yazar bulunması, dikkat ve geliştirme etkinliğine işaret ediyor. MCP ile AI destekli elektronik tasarımın güncel ilgisi de görünürlüğünü artırmış olabilir; ancak bu veriler tek başına gerçek kullanım veya tasarım kalitesi kanıtı değil.

Vibe-Research, kişisel yatırım araştırmasını AI destekli sohbet, piyasa verileri, şirket incelemesi ve araştırma kayıtlarıyla tek bir çalışma alanında toplar.

Neden yükseliyor · 84 günlük yaşına göre 2.588 yıldız ve son 28 günde 34 commit ile görünür ilgi ve yakın dönem geliştirme faaliyeti var; AI Agent ile yatırım araştırmasını bir araya getirmesi de güncel bir kullanım alanına denk geliyor. Ancak son 28 gündeki 3 farklı yazar, katkının sınırlı bir ekipte yoğunlaştığını gösteriyor; yıldızlar benimsemenin veya ürün kalitesinin kanıtı değil.

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dang

Your free book and audiobook laboratory. Turn the PDFs you own into chapter-marked M4B audiobooks, read-along books and bilingual editions,

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

the agi compiler: records llm agent behavior, proves what repeats, and compiles it into verified, sandboxed wasm binaries that run for micro

Self-Hosted LLM Code Review Agent for GitLab, Forgejo and GitHub. Local LLM support

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama

The Distillery. A Token Optimization Proxy

Native PowerPoint (.pptx) generator tool for Open WebUI — JSON spec in, native charts/icons/layouts out. MIT.

Learn Agentic AI, Deep Learning, Agentic Engineering, RAG and Multi-Agent Workflows.

Run and serve local models headlessly

Open-source AI model aggregation platform with web/admin dashboard, agents, image/video/audio generation, OpenAI-compatible API, wallet bill

开源 Windows 本地 AI 工作台｜OpenAI-compatible + Claude CLI，99 个桌面/Office 工具，可回退文件操作与可视化多 Agent 工作流。

Frontier model solution tracing, then made the prompting skills

llambda.lisp inferencer for LLMs in GGUF format

【书籍榨干器 v2.2.0】AI拆书+整合 Skill — 拆解：epub/pdf/md → 结构化完整拆解（概念/金句/反模式/行动清单）；整合：几百本拆解 → 主题知识手册（原料包+二轮加工，629本→93万字符实测）

all human experts into AI agents

GitHub discovery & LLM evaluation engine with automated follow, star, and auto-unfollow management.

信息的尽头，应该是行动 · Self-hostable AI information engine: multi-source aggregation, cross-source event dedup, AI curation, info-to-action loop

Session Recorder by Proofline. Free, open-source Chrome bug reports with annotations, voice, screenshots and one-click GitHub issues.

Community pain-point mining CLI and AI-agent skill for micro-SaaS and indie product ideas.

A practical Generative AI engineering lab exploring LLM foundations, tokenization, deployment strategies, and real-world AI system design.

Auto-generate and maintain a documentation wiki for any repo — native Claude Code plugin (/openwiki:wiki) & OpenAI Codex skill. A faithful p

LM Studio Local LLM Manager Pro Desktop Setup Guide — Chat with local AI models through a clean desktop GUI — no coding required. Windows de

Turn your workday into structured workflows agents can execute. 100% local, served over MCP.

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every g

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real dep

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kern

Claude Code skills that make Claude (Fable) the conductor of AI worker fleets: many parallel OpenAI Codex workers plus Opus design agents, o

OpenCode plugin for automatic API-key failover and rotation across multiple provider keys

Personal academic and research portfolio focused on AI, low-resource Urdu NLP, RAG systems, machine learning, and computer science.

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe