Havuz

Self-hosted, sharable kanban for humans and agents. One 4.5 MB binary, 4.5 MB of RAM, 10 to 60 tokens per agent reply, starts in 2 ms, zero

OpenConnector, SaaS hesaplarını bir kez bağlayıp bu hizmetlerin Actions'larını AI agents için SDK, CLI, MCP, HTTP ve OpenAPI üzerinden sunan bir connector gateway'dir.

Neden yükseliyor · 90 günlük yaşına karşılık 5.903 yıldız, son 28 günde 186 commit ve 15 farklı yazar güçlü ilgi ve geliştirme aktivitesine işaret ediyor. SaaS bağlantılarını agent'lara sunma ihtiyacına birden fazla arayüz ve self-hosted seçeneğiyle yanıt vermesi dikkat çekmesini açıklayabilir; bu veriler tek başına benimsenme veya kullanım kalitesini kanıtlamaz.

GonkaRouter account farm + 9Router auto-inject daemon. Full registration flow, key verification, systemd units. Zero dependencies — Python s

Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

全平台加密音乐格式转换器（网页版+命令行）：网易云 NCM / QQ音乐 QMC / 酷狗 KGM / 酷我 KWM 解密与转码，代码从零自研，MIT 协议

Self-hosted mobile web chat UI for Claude Code — drive your real local claude CLI from your phone. Same CLAUDE.md, MCP, skills, login; any g

Автономный YouTube Music для Яндекс Станции: голос, веб-панель и CLI

Agent-first AI SEO (AEO/GEO) operating platform

Run coding agents autonomously with isolated Git worktrees, independent verification, and human-controlled integration.

Remote-control the Cursor / CodeBuddy IDE on your machine — watch sessions, approve actions, and send tasks from your phone.

Close the lid and walk away — every window, desktop and terminal on your machines, live in any browser. E2E-encrypted, no open ports, no cli

General-purpose agent in one static Go binary: console TUI, ACP server for editors, OpenAI-compatible API with embedded web UI, Telegram gat

Javinizer written in Go and Svelte. This is a modern replacement for the original Javinizer. (NSFW) Organize your local Japanese Adult Video

DevOps secrets base: lightweight, self-hosted secrets manager in a single file

oly runs coding agents and long-running commands in persistent, supervised terminal sessions. The daemon owns the PTY, so you can close your

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Self-hosted remote terminal for iPhone, iPad & browser — attach tmux and run Claude Code, Codex, or any CLI agent from anywhere. Free for on

跨 agent 的 skill 管理器 + skill 推广工具，欢迎fork和pr。管理你所有 skill ，创建技能自带讲解pdf或ppt。支持各种Agent。

Open-source lead finder and cold email workspace. Describe a customer, get named people with labeled emails, then write, send, and automate

Anything to API (万物皆可2API): put an AI agent, a script, or even yourself behind an OpenAI-compatible API

Round-robin proxy for multiple Claude Max subscriptions — multiply your Claude Code throughput with automatic OAuth token rotation and trans

SSH port-forwarding manager with a TUI — toggle local, remote and SOCKS5 tunnels from one screen. Single Go binary, background daemon, autos

Gray is an open-source (MIT) AI agent harness shipped as one static Rust binary. Bash-only tools, resumable JSONL sessions, a self-compactin

One command deploys a censorship-resistant VLESS+Reality proxy server. Perfectly configured out-of-the-box. Relay nodes supported.

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistra

Project Management for the agent era

LAN Sheriff watches which servers your network talks to. Self-hosted, no account. Observes only; blocks nothing. Built by 291 Group.

Private messaging for your AI agents. Free to self-host on Cloudflare. Direct chats, groups and a durable inbox.

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI a

Aizen is an AI coding agent that lives on your PC or VPS. Control it from your phone while it autonomously fixes code, runs tests, and repor

One command to run the AI coding CLI you already pay for (Claude Code, Codex, Cursor, Gemini, Grok, aider) on a Tailscale-only Hetzner box —

Your terminal, anywhere. Run an agent or command on your computer and use it from any browser. Developed by Pilot Protocol.

OpenClaw Companion / OpenClaw 中文助手：中英双语、安全编排官方 OpenClaw 安装、配置、检查、升级、备份与诊断。社区项目，非官方。

Local-first AI action assistant for operators: memory, skills, tools, and permission gates to turn work into controlled action.

The network layer for AI agents. Reach your customers' on-prem data, show what you build, keep it running — through one relay that your mac

AI-powered repository agent for GitHub, GitLab, Gitea, Azure DevOps. Issue triage, PR analysis, merge queue, notifications, dashboard, backu

A fully guided Python CLI tool for creating Navidrome .nsp smart playlist files — featuring nearly 300 presets, 100+ fields, nested rule gro

Self-hosted file and note sharing that cleans up after itself.

expose localhost to the internet instantly. zero-dependency tunneling engine with a custom 9-byte binary multiplexer, interactive bubble tea

Share files with simple codes instead of links. Fast, live server or self-hosted and open-source.

Self-hosted PWA to control Claude Code, Codex, GitHub Copilot or any terminal from your phone or desktop. Single Go binary streaming tmux/ps

Post-quantum age key generation and paper backup tool with QR codes

Google Drive for AI agents — share files with your team, share context across your agents. Open source, no server required.

Lightweight Linux sandbox for AI agents. Kernel-native isolation (namespaces, cgroups, seccomp, Landlock) with REST API, MCP bridge, and web

Open-source email infrastructure for AI agents.

Turn one machine into a private ChatGPT for a whole room. One command sets up Ollama, Open WebUI, RAG and an OpenAI-compatible API sized to

Offline-first Go CLI for engineering teams to observe AI adoption, compare estimated coding-tool costs and inspect bounded local delivery ev