Havuz

Run AI coding agents in parallel on one git repo and safely auto-merge their work — only changes that build and pass tests land. On top of p

AI brain for your Paperless-ngx archive — chat with your documents via local (Ollama) or cloud LLMs, with agentic tool use, semantic search

Self-healing, config-as-code stack for the OpenCode AI coding agent — one key, 17 curated OpenRouter frontier models (GLM/DeepSeek/Gemini/Qw

LLM-first SEO skill for AI coding assistants. Features 16 sub-skills, 10 specialist agents, 89 python scripts, and 160+ markdown marketing s

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.

Lightweight observability for multi-agent AI pipelines. Self-hosted, no cloud dependency — add two lines of Python and see real-time agent e

A durable job engine for Elixir, on Postgres. Jobs are built from memoized steps — retries resume work instead of redoing it. Budgets, workf

Janux - One component, two faces: UI for humans, MCP tools for AI agents. The agent-native fullstack framework.

Caspian, AI agent'ların birden fazla mesajlaşma kanalında ortak bir handler üzerinden insanlarla iletişim kurmasını sağlayan bir SDK'dır.

Neden yükseliyor · 69 günde 973 yıldız, projeye erken dönemde kayda değer ilgi olduğunu gösteriyor. Çok kanallı agent entegrasyonlarını tek arayüzde toplama vaadi bu ilgiye uygun; ancak son 28 günde commit ve farklı yazar görünmemesi, ilginin devam eden geliştirme veya topluluk katkısına dönüştüğünü doğrulamıyor.

Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.

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

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

让Codex向你呈递公文并接受批示圈阅

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and gar

Wazuh MCP Server: AI-Driven SOC Automation

Real-world percentile benchmark for LLM inference servers: 1% A/B resolution, offline HTML reports. I am now on X also: https://x.com/bkuype

An educational macOS app: build and chat with a tiny language model, trained on your Mac

Local-first CLI that reads your Spec-Driven Development artifacts and recommends the best value-for-money AI model to implement them. Powere

Angles Code CLI — 2MB coding agent with 2GB powers

Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.

Store every accomplishment. Tailor every application. Own your career data.

AWS-native knowledge graph RAG framework. Runs GraphRAG, LightRAG, HippoRAG 2 and RAPTOR on one shared index, each selectable at index and q

A benchmark for infrastructure agents.

Long-running autonomy for Pi: draft goals, build projects from specs, run audited task queues, and recover interrupted work. Independent aud

채용공고(JD)를 지원·면접·설명 가능한 IT 인턴 프로젝트로 바꾸는 한국형 AI 스킬 · JD → 오픈소스 선정 → 코드 분석 → 이력서·면접팩

Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Curso

国内主流 LLM Coding Plan 真实用量榜单：厂商宣称 vs 用户探针实测 vs 官方 monitor 三方对照。一眼看穿动态倍率、积分通胀、隐藏限流——买之前，先查账。

Your engineering taste, in every coding agent. Shadowclone learns your rules and delivers them as skills to Claude Code, Codex, Cursor, Pi,

盛大泡泡堂之 Kimi K3 满血复刻

The open memory layer for collective agent awareness — a vendor-neutral MCP service for shared AI-agent memory.

Ask for the symbol, not the file. Token-efficient MCP server giving AI coding agents symbol-level reads of TS/JS, Rust, Python, Java, Go,

Native runtime, integrations, and reproducible packaging for BTL-3 and BTL-3 Compact

MusePi — desktop-first AI coding assistant: Electron GUI + TUI/CLI + daemon + desktop companion. Native video understanding, MCP, advisor, m

Automatic movie clipping for YouTube Shorts. Scene detection, LLM scoring, face tracking, subtitles, vertical crop.

跨平台、本地优先的 Coding Agent 工作台：持久对话分支、Workspace 与 Session、多模型、Goal 与 Agent 编排、可自构建 Bots 和 Bot-to-Bot 协作。支持 macOS、Windows、Linux 桌面与无头 Web。

PenguinHarness, agent uygulamalarını oluşturma, değerlendirme, iyileştirme ve dağıtma süreçlerini otomatikleştirmeyi amaçlayan açık kaynaklı bir platformdur.

Neden yükseliyor · 71 günde 2.392 yıldız ve son 28 günde 156 commit dikkat çekici bir ivmeye işaret ediyor; ancak 5 farklı yazar, faaliyetin küçük bir katkıcı grubunda yoğunlaşabileceğini gösteriyor. README'deki maliyet ve benchmark üstünlüğü iddiaları proje tarafından sunulmuş; bağımsız doğrulama bilgisi verilen ölçümlerde yok.

Multi-Agent self-correcting reasoning engine

The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understa

NEURA Office: native Word, PowerPoint and Excel for Open WebUI. LibreOffice-compatible OOXML. MS365 assistant planned.

A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insi

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

Open-source AI-powered subtitle generation and natural language translation platform for video and audio.

Customized New API gateway with SnowAPI UI, LinuxDO OAuth, invitation codes, usage analytics and model health monitoring.

Dify 1.19-compatible MCP server + CLI — 193 tools for building, testing, publishing, and migrating Dify workflows, with stdio/HTTP MCP, DSL,

On-device AI agent for Android local OpenClaw gateway, bring-your-own-key (NVIDIA/OpenAI/Anthropic/Gemini), UI automation via Accessibilit

RepoDoc is a lightweight, zero-dependency utility that scans any project directory and generates a complete Markdown document containing the

A 125-task benchmark for knowledge-mediated implicit associations and retrieval blind spots in long-term agent memory.

保留排版的文档翻译工具：PDF / Word / PPT / Markdown / 字幕，图片、公式、表格与版式原样保留，译文落在原文位置。支持多语言方向、扫描件 OCR 与本地离线翻译（Ollama）。Windows / macOS 免安装，双击即用。