Trending Repos

A 7-layer memory operating system for Hermes Agent that provides persistent memory with features like Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection.

Why: It enables local AI memory management with various functionalities, allowing for efficient and contextual data retrieval and storage.

Self-hosted dev sandboxes with preview URLs. One command. No Kubernetes, perfect for coding agents and Saas factories

Superlog is an open-source observability tool that uses AI agents to automatically detect and fix software issues.

Why: It helps developers monitor and maintain the health of their applications with minimal manual intervention.

Self-hosted dev sandboxes with preview URLs. One command. No Kubernetes, perfect for coding agents and Saas factories

A comprehensive desktop application package for advanced ChatGPT interactions and management.

🚀 Ultimate ChatGPT Pro Toolkit 2026 – AI Automation, Plugins & Workflow Enhancer

Open Dungeon — the first easy-to-use, fully local AI roleplay app. Story and inline scene images generated 100% on your machine (Gemma 4 QAT via Ollama(and others) + FLUX). No accounts, no API keys, no cloud.

The open-source alternative to Minecraft: Java Edition, a complete block-survival game in ~45,000 lines of Swift + Metal. Zero dependencies, fully deterministic, singleplayer for now. Not affiliated with Mojang or Microsoft. We lowkey need y'all to submit bug reports cuz there are so many 😭

Community model zoo + knowledge base for Apple Core AI (iOS/macOS 27): Qwen3.5 & Gemma 4 converted end-to-end, verified on-device (iPhone 17 Pro GPU/ANE), conversion gotchas, custom Metal kernels, Swift runner

AI 每日新闻简报 · GitHub 热门 + X 热门文章 + 行情技术分析 · 23 个数据源聚合 + LLM 中文摘要 · 本地或 GitHub Actions 部署

家长可控的自建儿童视频流媒体播放器：无广告、无推荐流、封闭内容花园 · Self-hosted, ad-free kids video streaming player with parental controls — Cloudflare Workers + R2 and native SwiftUI (iOS / iPadOS / macOS)

Sovereign, depth-adaptive AI memory. Open source. Local-first. Model-agnostic.

An AI-powered Personal Knowledge Assistance system with a nine-person AI team baked in. Plain markdown. Any LLM. Yours forever. Picks up where you left off across sessions. Built on the ICOR® methodology.

Give a query, get a dataroom. Pi + self-hosted Qwen3.6 research harness on a single L4.

可自部署的 Grok 注册机 Web 控制台，支持 Docker、DrissionPage 自动化、邮件后端配置和本地账号号池管理。

Open-source, local-first, read-only AI SRE: clusters alert storms, investigates root cause over your live systems, proposes human-gated fixes.

AI Agent lives in your project. Open-source, self-hosted, multi-provider, highly scalable, powered by .NET.

Open-source alternative to Claude Co-Work built by Claude Mythos 5. with BYOK

Iron-Man-style voice assistant + holographic HUD for Hermes Agent. Local Whisper STT, ElevenLabs voice, agent-summoned media panels, runs on your own hardware.

国内首个企业级 IT 运维多 Agent 自动化平台 — 基于大语言模型的智能运维解决方案。ITOps Agent Platform 是一个企业级全栈运维自动化平台，通过可视化工作流编排，将多个AI Agent组合成智能运维自动化流水线，实现服务器管理、告警处理、故障诊断、日志分析、脚本管理、定时运维任务的自动化执行，支持火山引擎/OpenAI双LLM模型。

A Pi-hole DNS visual dashboard. Blocking is represented by an interceptor ship destroying 'blocked query' baddies, space invaders style. Now supports AdGuard!

Kostenlose, self-hostbare Open-Source-Rechnungssoftware für Deutschland · E-Rechnung (XRechnung/EN 16931, offiziell Schematron-validiert), GoBD, §14 UStG, Kleinunternehmer §19 · per Claude Code (MCP) in natürlicher Sprache steuerbar · AGPL-3.0

A curated directory of 60 self-hostable, open-source projects worth knowing about.

Free, open-source email signature generator. Single HTML file, no sign-up, no server.

Agyn is an open-source platform that moves agents from laptops to company infrastructure with the controls enterprises need.

Self-hosted SSH connection manager. Open-source alternative to Termius.

RustDesk Pro - Open-source remote desktop with self-hosted server option. Official page with installation notes, activation guidance, and configuration tips.

Your favorite offline self-hostable maps. City, Country, Planet, you choose.

Open-Source data analyst your team actually owns. Ask in Slack, on Mac, or via MCP. Byaan learns your business. Read-only by design

Pi hole Pro - Network-wide DNS ad blocker for all connected devices. Includes setup guide, feature overview, and download instructions.

Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems

Universal crypto-first platform for payments, subscriptions and software license management

在自己的 Mac 上搭一套常驻、自愈、走订阅、墙内也能用的自托管 AI 伴侣 · 人看版讲思路，机看版给完整规格 · 文 / 小C & Grace

Self-hosted browser session replay built on S2 with live tailing

Compartment is a self-hosted application deployment system for teams that want to ship and share internal, private, or public web apps without building their own platform stack.

The coordination, measurement, and quality layer that subgen never had. A peer service for the *arr family that adds calibrated audio-language detection, provider success leaderboards, and (v1.1) an in-app Whisper tuning lab.

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

Agentic runtime in Rust — persistent, supervised agents. Self-hosted, local-first, zero telemetry. Apache 2.0.

Open-source GEO / AEO skill for AI visibility readiness: check robots.txt, llms.txt, schema, citation signals, competitor gaps, and buyer prompts

Self-hosted PWA for a single household — shared calendar, chores, meals, school agenda, health records and a family wall. .NET 10 + Angular 21. Pair-programmed with Claude Code Opus 4.7.

The factory for custom internal software, purpose-built for human2agent work.

Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billing, no card on file.

CPU-only, pure-Rust implementation of LiquidAI's LFM2.5-8B-A1B LLM

Moved to EKKOLearnAI/hermes-web-ui; this repo is kept for historical releases.

The open-source legal AI agent. Documents stay on your machine; redlines land in Word. Fork of OpenCode.

真机 RPC 中继：把只能在真机/特定环境跑的函数封装成 HTTP 接口（Go + WebSocket，React 控制台，分组路由、单节点）

Self-hosted LLM gateway. One Go binary turns your Macs and Linux boxes into a private inference cluster — multi-machine routing, sharding via llama.cpp-RPC, per-user keys + quotas + audit, OpenAI- and Anthropic-compatible APIs behind one endpoint. Point Cursor / Claude Code / Aider / SDKs at it.

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

Open-source, self-hostable WordPress fleet management: backups, updates, uptime monitoring, security, and image optimization for every site from one dashboard you own. A self-hosted MainWP and WP Remote alternative.

More than just Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.

Fully offline tiny LLM chatbot on the ESP32-S3 Cardputer ADV - 3M params, Q4 weights baked into the firmware, ~7 tok/s.

Ollama Model Test - Figure out the best model for the task

Plug in a USB. Get an offline AI coding agent on any laptop — Windows, macOS, Linux. opencode + Ollama, pre-built for 5 targets, zero install on the host.

Self-hosted Chinese personal memory graph. Six sources, two LLMs, one graph.

A landing page for your services, dashboards, and documents, discovered automatically from sources such as Docker, Kubernetes, and Tailscale.

Self-hosted native-Rust runtime for real-time voice agents. Own the stack: one binary in your own VPC or air-gapped, no hosted control plane. pipecat-compatible pipeline, in-process SIP/RTP, single-process call density. Apache-2.0.

OpenXiv is an AT Protocol preprint server with source-based submissions, public provenance, typed endorsements, OAI-PMH, and Bluesky federation.

Self-host your own AI app builder: FOSS v0/Lovable like.

Real-time bKash SMS transaction monitoring for Android — capture, store, and sync P2P payments to your own Cloudflare backend for automated payment verification.

Self-hosted Docker update manager — manual-approval alternative to Watchtower

Self-hosted bilingual RSS reader · inline DeepSeek translation · FastAPI + vanilla JS, zero build

Open-source AEO (Answer Engine Optimization) infrastructure — every page, dual-marked. Markdown twins for AI agents alongside HTML for humans, picked by HTTP content negotiation.

For young investors who want to create a dividend portfolio that will yield them a living wage in 2045, this tracking app will help you track your portfolio and use its features to get a top-notch perspective on the portfolio and make it easy for you to use.

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker compose up.

C2 server fingerprinter — Cobalt Strike, Sliver, Mythic, Havoc, Brute Ratel

Open-source, self-hosted AI video editor: turn long videos into captioned 9:16 shorts — and edit by chatting. BYO LLM key. AGPL-3.0.

AI coding agent workflow engine for structured task lifecycles.

🎬 16-role AI film studio · End-to-end short video pipeline · Multi-agent · Self-hosted

A bestiary of internet trackers, populated by your Pi-hole. ~19,000 entities, deterministic 16x16 RPG sprites, built on Tracker Radar + Pi-hole v6.

Your agent team, on your machine. Open-source harness for multi-user Claude agents.

Dockerized nginx mimicking Microsoft IIS 8

AXI4-Stream protocol compliance checker skill for Claude — open-source alternative to commercial EDA tools

A self-hosted 3D AI virtual world for Agent Harnesses like OpenClaw and Hermes.

A self-hosted, interactive learning environment. Run courses, flashcards, and quizzes entirely on your own machine.

an open source alternative to @heyclicky

Stop getting your stops hunted. SL/TP never touch your broker - only fires when the underlying actually breaches your level. And skip the options chain: drag your levels on the chart, we auto-pick the strike + DTE + contracts. The first open-source platform that does both.

Nexus Trade Bot is an open-source millisecond-level high-frequency crypto market-making and grid trading system for major exchanges, with web console, automated order management, WebSocket sync, risk controls and one-click server deployment. 开源毫秒级高频加密货币做市与网格交易系统，支持主流交易所、网页控制台、自动挂单、风控、自托管部署。

High-performance asset optimization for FoundryVTT. Convert scene backgrounds to WebP and audio to OGG Opus directly in your browser using multi-threaded WebCodecs for faster load times and less bandwidth.

Topside — mobile-first web cockpit for a headless Linux VPS. Terminal, files, monitor, media + a real remote browser in a desktop-style UI. Single Next.js app, no database, no agent.

Beginner-friendly nginx setup and virtual host manager for Linux. One installer, one easynginx command. Reverse proxies, SSL via Let's Encrypt, security hardening, backups and rollback — all distros, no surprises.

Stream Over the Air TV, IPTV, Youtube, Twitch and more directly to Discord

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

Self-hosted 多用户 WeChat / 微信 AI 智能体控制台，支持 Web 管理、Docker部署、MCP、Skills、记忆、定时任务、沙盒执行和长期运行，支持分享AI Bot给团队成员。

Run the LLM Swarm Router on machines to distribute Local Ai to the Swarm - More Machines - MORE SPEED

Fast, lightweight SOCKS5 server in Rust — TUI dashboard, headless mode, secure by default.

Plug-and-play homelab dashboard in one container — GPU, local-AI model VRAM, Docker, systemd and host health. One page, no Prometheus/Grafana.

Self-hosted multi-user Apache Spark notebooks — PySpark + Scala, per-user kernel pods, MinIO IAM storage, OAuth. One Helm install. Apache-2.0.

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Your AI team. At home.

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

axon

Cross-platform clipboard sync over WebSocket. One small Rust binary; runs on Linux + Windows + MacOS. LAN/VPN-first, auto-generated TLS.

Self-hosted Shopify and Google Ads operations dashboard for ecommerce teams

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command. No Electron, no Python, offline-first.

Free AEO + AI search readiness plugin for WordPress. Schema, llms.txt, AI crawler controls, brand sentiment + citation tracking.

轻量 VPS / 服务器管理 Telegram Bot，支持 SSH 管理、批量导入、质量测试和安全白名单。

自托管商品视觉工作台：商品识别、AI 图片生成、二次编辑与电商营销素材套包。

Self-hosted personal knowledge brain for Telegram, WhatsApp, n8n, Groq, and Obsidian. Save links, voice notes, and images; auto-summarize, categorize, tag, transcribe, set reminders, share guest access, and ask questions later from your Markdown knowledge vault.

Run Pi coding agent isolated in a Docker Sandbox microVM with a local llama-server as the inference backend

AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private.

Translate books and documents with LLMs, featuring glossary extraction, review, and polishing pipelines.

Self‑hosted AI agent control plane with local LLM planner (Ollama) + Bitcoin Lightning‑style micropayments (L402‑inspired mock). TypeScript + Docker.

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

🧹 Clean up unused Docker images — web panel or scheduled console daemon. Select & delete, interval/cron auto-cleanup, age guard, multi-arch image.

Self-hosted YouTube channel downloader & viewer

Native SwiftUI app for iOS to monitor, manage, and automate a Proxmox VE homelab.

Temporary email service - self-hosted alternative to temp-mail.org

A source-first map of Generative Engine Optimization (GEO), AEO & AI search — built on official engine docs, not vendor hype.

Code from your phone — self-hosted mobile web UI for terminal coding agents (OpenCode chat + real terminal)

把财经博主的喊单变成可追踪的战绩:AI 标立场 · 记转向 · 回测跑赢大盘 | Turn finfluencer noise into trackable signals — AI stance labeling, flip radar, beat-the-market backtests. Self-hostable, not financial advice.

A simpler self-hosted alternative to Open WebUI. Bring your own OpenAI-compatible endpoint.

A self-hosted markdown note-taking app. Fast, simple, private. Access your notes from any device.

Extract a person into an AI agent — through an 8-week therapist-style interview, not a form. The open-source alternative to $4K AI clone courses.

Open-source debrid service. Add a magnet, get a stream.

Bliish.space is an ultra-fast, lightweight, open-source social platform with customizable profiles, no ads, no tracking, and simple, affordable self-hosting.

Production-ready Kubernetes deployment manifests for the OCTO platform — Kustomize bases, environment overlays, and secret templates for all services.

LiteGist: A modern standalone pastebin service powered by Node.js & SQLite. Supports multi-file Gist management, Git-like version history, Sub-Store proxying, and subscription conversion. Fast, secure, and PWA-ready for an immersive "Private Gist" experience.

Local-first markdown notes with a first-class MCP server. 16 tools + 2 resources for Claude Code, Claude Desktop, Cursor and any MCP agent. Per-folder permissions, semantic RAG via LanceDB, single Bun binary. AGPL.

One-click installer for Google's Gemma 4 12B — optimized to run on 8GB laptops, 1M context, native multimodal. No terminal. Win/Mac, MIT.

Enterprise-grade AI workspace for legal teams. Self-hostable. AGPL-3.0.

Plateforme IA juridique souveraine, auto-hébergeable et open-source. Bring Your Own Key, agrégateur de modèles FR/EU/US, RAG pgvector, orchestration multi-agents.

Deterministic cost / loop / time budgets · full observability · crash-resumable runs · human-approval gates · a memory you own. Self-hosted. Your keys. No telemetry. Point it at your existing agents - one env var.

🐙 The Go backend powering OCTO — an open workplace built for humans × AI agents. REST & WebSocket APIs, Lobster (AI agent) orchestration, and WuKongIM real-time messaging control plane.

Self-hosted SEO crawler for Claude — Screaming Frog-level audits, unlimited pages, 1-click install. 19 MCP tools.

Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command

Operating system for the KODE NAS pebble — a beginner-friendly Raspberry Pi 5 NAS. Forked from CasaOS with a custom dashboard, first-boot wizard, app walkthroughs, and OLED display daemon.

Self-hosted webhook inspector. Single binary, SQLite, no external dependencies.

Self-hostable, source-available WhatsApp CRM built on the Meta WhatsApp Cloud API — chats, contacts, templates, broadcasts, and a visual automation builder.

The SEO + AI-search (GEO/AEO) optimization toolkit for Claude Code — two-score audit + opt-in fixer. Built for 2026-2027.

Your Linux system has a story to tell. Hosomaki is the moment it finally finds its voice.

Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-layer intercept.

An unofficial Android client for self-hosted Bambuddy.

Doktainer is an open-source, self-hosted platform for managing servers, applications, containers, domains, SSL, backups, and deployment operations from a single web panel.

Real-time token, cost, and AI limits widget with multi-device sync for Claude Code, Codex, OpenCode, Hermes, OpenClaw, Cursor, and Antigravity. | 为 AI Tools 打造的即时Token、成本与限额监控桌面组件，支持多设备同步

Deploy a complete, self-hosted AI stack on your own server with one command. Includes Ollama (LLM), AnythingLLM (chat UI), LiteLLM (AI gateway), Whisper (STT), Kokoro (TTS), Embeddings (RAG), and MCP Gateway. Most services run locally; LiteLLM optionally routes to external providers. Supports NVIDIA GPU (CUDA) acceleration.

Maverick AGI v2.5 – a fully offline, terminal‑first personal AI assistant that runs locally on your machine. It speaks, listens, sees, searches the web, executes terminal commands, solves math, manages goals, and remembers everything you teach it. Works entirely offline by default, with optional cloud‑LLM acceleration for speed.

Use many on device and cloud models with Apple's Foundation Models framework in iOS and macOS with a full chat experience.

The open-source GEO engine that gets your brand mentioned in ChatGPT, Claude, Gemini, Perplexity, and Grok. MIT, by Shadow.

Self-hosted, OpenAI-compatible AI gateway for organizations — multi-provider (Azure/OpenAI/Anthropic/Gemini), revocable per-allocation credentials, usage & cost tracking, and an OpenAI Codex–ready /v1/responses endpoint.

Local-first macOS activity tracker with AI-powered classification, a daily commonplace book, and an MCP server for Claude.

An agent that builds agents — closed-loop AI system that interviews, designs, tests, and ships standalone Python agents.

Zero-Trust Semantic Scraper & Firewall Proxy for AI Coding Agents. Intercepts and neutralizes web-scraped prompt injections locally before they hit your terminal window.

Self-hosted, open-source AI resume builder for software developers.

Parental controls for Technitium DNS — self-hosted dashboard with optional ASUS router integration (MAC kill switch, transparent DNS Director, DoH/DoT IP blocklist).

Unofficial Windows GUI launcher for LocalAI — running LLMs, vision, and voice with a simple button interface. Original engine by @mudler.

Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

Read-only supply-chain scanning for Hermes Agent, powered by Perplexity's Bumblebee. Daily scans, Telegram alerts, JARVIS narration.

A Youtube-Inspired client for jellyfin written in Svelte.

Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.

The old advice to avoid Windows for local LLMs used to be right. It isn't anymore. The fixes for display-GPU desktop crashes and WSL memory limits, from people who run a 5090 daily.

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

Local-first log analysis with PII redaction, threat detection, anomaly detection and LLM insights — CLI, web dashboard and REST API

The terminal-first Android app for durable SSH/tmux workspaces, programmable launcher widgets, SSH forwarding, and CLI-native development.

基于 Cloudflare Email Routing 的高性能自托管邮箱服务

Open-source Answer Engine Optimization platform — track how ChatGPT, Google AI Overview, Google AI Mode, Perplexity, Claude, and Copilot mention your brand.

Interactive CLI wizard to deploy and manage Frappe/ERPNext on Docker — from local dev to production with Traefik, MariaDB/PostgreSQL, custom image builds, and S3 backups.

Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7

Put your coding agents in your pocket: a mobile control plane for local agent sessions

AI commit messages from your local LLM — Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes.

A self-hosted AI brain for the Vector robot by Anky Labs

🤖 A self-hosted Discord bot powered by an LLM with tool calling & per-channel context

Zero Trust for AI agents. Generates and protects MCP servers for both internal copilots and customer-facing agents. Apache 2.0, self-hosted.

A fully local multi-agent AI board — CEO, CTO, CFO, CPO, COO running on your own GPU/CPU. No cloud. Just Local Models.

Recovery Operating System for Ecommerce/D2C. Ten Claude Code skills for Core-Update recovery, AI search visibility, decision-maker PDF outreach, channel economics, GSC + AI-citations tracking. Built from real 2026 ecommerce recovery cases. MIT, externally audited.

Claude Skill for Generative Engine Optimization and agent readiness. Get cited by ChatGPT, Perplexity, and Google AI Overviews. Expose MCP, llms.txt, and OAuth to AI agents.

A simple, clean, and elegant navigation page designed for the modern web.

Local-AI autocomplete & spell-correction for macOS — 100% on-device (llama.cpp + Metal), menu bar app, press Tab to accept.

Open-source web hosting management platform — self-hosted alternative to WHMCS

Mobile-first remote control for coding agents, with self-hosted relay, Telegram support, and local-first privacy.

Son of Anton, reimagined as a web app — Node + WebSocket + node-pty + xterm.js, zero Electron.

Cloudflare-native AI customer support platform with Worker API, admin dashboard, knowledge base, multi-channel conversations, Telegram Bot, and embeddable Web Chat Widget. / 基于 Cloudflare 的 AI 智能客服平台，包含 Worker API、管理后台、知识库、多渠道会话、Telegram Bot 和可嵌入 Web Chat Widget。

⚡ Intelligent routing layer that auto-selects the right LoRA adapter for each task in your local LLM agent loop.

LM Studio — local llm gui.

LobeChat — ai chat ui.

GPT4All — local chatgpt.

KamehaDB is a cross-platform database GUI - AI. Support query via human language

Curated list of open source alternatives to proprietary software.

Lightweight, self-hosted WebSocket relay for local-first applications. Enables secure end-to-end encrypted communication between your own devices using the Noise Protocol (XX handshake).

Configuration templates, routing engines, and global instructions to integrate local Gemma 4 E2B models as high-efficiency subagents in Google Antigravity IDE.

Turn speech into text. Free, open source alternative to Wispr Flow.

Small, sharp, agent-agnostic skills that keep an AI agent's work honest.

A free, open-source alternative to Google’s Places API.

Android chat client for LM Studio local server with OpenAI-compatible API, MCP/server tools, chat history, and LAN support.

📚 Single-file browser viewer for academic PDFs powered by your local LLM (LM Studio / Ollama). 5-section summaries + suggested Q&A + figure/table understanding via VLM. Built for live research workshops and session chairs.

🦁 Local AI for Consumer GPUs — Run powerful LLMs on GTX 1060/1080. No cloud. No subscriptions. Built on llama.cpp + CUDA.

A simple example for a game using CogentLM inference

Terminal-based multi-model comparison, benchmarking, and evaluation tool for Ollama. Zero dependencies, one file.

Local-first Markdown knowledge base with a built-in AI second brain. Plain .md files, wikilinks, graph view, inline databases, private GitHub sync — and local LLMs that search (in feature), link, and reason over your notes.

Fast-ASDLC: 5x TTM with AI-native Agentic SDLC. Local-LLM first, Human-in-the-loop, Spec-driven. Built on DDD, Hexagonal Architecture, C4 Model & MCP. Features Meta-agents for self-improvement, Memory Bank for context persistence, and automated 100% test coverage. Everything-as-Code & Mermaid.js centric to save context window and slash token costs.

Open Source LLM — llama 4, deepseek v3, qwen 2.5, open source ai.

Build your own self-hosted cold email infrastructure — the open-source alternative to Smartlead/Instantly. Claude Code skill + full playbook.

Private, local-first AI assistant with Telegram, Discord, WhatsApp and Slack