Havuz

An infinite canvas desktop app for visually managing terminals

Local, zero-dependency dashboard for Claude Code: live token usage and context, lost-session recovery, full-text search, and approve tool ca

小红书/抖音/快手/视频号/B站 自媒体账号体检+爆款拆解工具。扫同赛道找对标、拆爆款为什么爆、诊断为什么没人看，顺手出可粘贴仿写初稿。支持带货电商模式。支持codex, claude code, workbuddy

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

Vlad's Playbook — a 48-chapter operator field manual where every artifact is live, clickable, and forwardable. 31 interactive widgets, a sel

🏆 AI Hackathon 2026 @ UC Berkeley Intelligent context management for developers

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

A practical Codex skill for evidence-backed repository health audits

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.

ClickClackClaw - The chat app with claws.

📚 Read a top-tier AI paper in 5 minutes.

Open-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identif

Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.

Real-time multimodal AI pipelines on Apple Silicon

Task management system for humans and agents in Obsidian.

Двенадцать площадок РФ и Китая (11 маркетплейсов + Циан) как MCP-серверы и 15 Agent Skills: Wildberries, Ozon, Яндекс Маркет, Детский мир, А

Subpool, ekiplerin yetkili AI abonelik ve API hesaplarını tek bir self-hosted gateway üzerinden havuzlayıp yönetmesini sağlar.

Neden yükseliyor · 25 günlük yaşına rağmen 83 yıldız ve son 28 günde 61 commit dikkat çekiyor. Commit temposu yüksek; ancak yalnızca 2 farklı yazar görünmesi katkı tabanının şu an dar olduğuna işaret ediyor.

Open-source Android workstation: native multi-window desktops, X11/Wayland, Termux and MCP automation. Shroot runs Linux, systemd, Docker an

A local emulator for enterprise SaaS APIs — Slack, Gmail, Google Drive, GitHub, Jira, Notion, S3 and more — with the real response shapes, p

Desktop multicam recorder for macOS: records your screen and webcam in sync, then Claude Code or Codex edits the final video — shot selectio

Full-stack ecommerce on Cloudflare Workers, D1, and R2 - with admin, Stripe, OpenNode, Lightning payments, and agent-ready APIs.

Vault-LD: an open spec for Markdown vaults as linked data. YAML-LD frontmatter + a shared `@context` = an RDF knowledge graph. Prose for hum

Run Claude Code against any AI provider. DeepSeek, Groq, Ollama, OpenRouter — your call.

This is the corresponding code for the O'Reilly book: Harness Engineering

墨台 VibeHolding：AI 时代全链路基建选型知识库（A–V 图廓 · 关系边 · 方案）+ 桌面/Web 客户端。本地优先，内容可 PR。

Open-source AI office assistant for your desktop: describe the result or file you want in one sentence, and Abu plans and does the rest. Loc

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

A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.

Your agent swarm as a live DAG: an orchestration graph with attempts, review gates, and evidence, in a herdr split pane.

Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison,

Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).

Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Comfy official local MCP.

Scan, classify (A/B/C/D) and sync AI-agent SKILL.md files across toolchains (Codex, Claude Code, WorkBuddy). Zero-dependency Python CLI.

🥝 Self-hosted memory gateway for AI companions — OpenAI-compatible proxy with vector search, memory heat, Dream consolidation and calendar-l

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

AI-powered Personal Knowledge Assistance in a folder. Built on the ICOR methodology. Plain markdown. Any LLM. Yours forever.

SV Number agent skill, AI agent’ların farklı ülkelerden tek kullanımlık telefon numarası alıp SMS doğrulama kodunu API üzerinden okumasını sağlar.

Neden yükseliyor · 51 günde 225 yıldız almış; agent tabanlı otomasyon ve telefon doğrulama ihtiyacının kesişimine odaklanması ilgi çekmiş olabilir. Ancak yükselişin nedenini doğrulayacak ek veri yok; README’deki 200+ ülke kapsamı iddiası canlı API üzerinden kontrol edilebilir, bağımsız olarak doğrulanmış değil. Son 28 günde commit ve farklı yazar görünmüyor.

Open-source stealth Chromium with engine-level fingerprint spoofing - de-Googled, drop-in Playwright, fully buildable and verifiable from so

一个本地优先的AI知识库系统（RAG），用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf（文本）、xlsx、cvs类型。支持mcp服务

Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automa

The Open Analytics design language as an agent skill: component recipes with type-checked source, token CSS, and a CLI. Works with Claude Co

🔎 深度研搜对话式多智能体 AI Agents，最适合系统学习 DeepAgents 的实战项目｜AI Deep Research Agent 实战 · LangGraph + RAGFlow + Tavily + FastAPI + WebSocket 从0到工程化落地。前后端

开源私域 AI 营销 SCRM 系统，Martech 获客引流利器， 智能AI客服 、销售 ReAct 自主 AI 智能体 全渠道聚合（抖音/小红书/快手/微信/WhatsApp/TikTok/Telegram）统一收件箱 独家 GEO 模块（生成式大模型引擎优化/AI 搜索占位

OpenCode Mobile — open-source Android client for the OpenCode AI coding agent. Run AI coding sessions from your phone against your self-host

A curated list of code samples and tutorials for building agents on Gemini Enterprise Agent Platform (previously Vertex AI).

Go from sitting next to one AI coding agent to running many in the background. Dark engineering with the pi coding agent: self-hosted, each

Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with

An MCP server for RenderDoc: Empowering AI assistants to analyze GPU frame captures and debug graphics pipelines.