Havuz

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

a terminal coding harness

EdgeCrab 🦀 A Super Powerful Personal Assistant inspired by NousHermes and OpenClaw — Rust-native, blazing-fast terminal UI, ReAct tool loop,

A minimal yet ready-to-use AI agent harness, built on best practices for frontier models.

Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients

A system prompt against AI sycophancy, backed by 42 sources on why models tend to agree with you.

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

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.

Fully local voice AI for iOS

Claude Code with the model slot left open. The full workflow, open source, on any model or provider.

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Web tasks that compile. Other browser tools tell your AI agent the click worked. chrome-agent reads the page back after every action and ans

Open-source email infrastructure for AI agents.

Marketing Studio is a self-hostable AI video ad studio for e-commerce: UGC product ads, reference-ad remakes, AI drama ads, and ad skits, po

ZEOS: a transformer operating system — priority-preemptive scheduling, protected mode, and deterministic replay for LLM jobs

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

Autonomous development loops for Claude Code, Codex and OpenCode. Adds planning, implementation, checks and cycle state to new or existing p

Azeroth World Editor (AWE): a 3D world and quest editor for AzerothCore servers with built in MCP support

SIRIN is a Python library for detecting and analyzing contextual inconsistencies in systems that use LLMs

Travel MCP server + CLI for AI assistants — flights, hotels, trains, cars, ferries, price alerts. No API keys, single Go binary. 1 smart MCP

The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your cont

Extreme weight + KV cache compression for LLMs on Apple Silicon (MLX implementation of Google's TurboQuant)

Universal memory runtime for AI agents

AI-powered SAST scanner that finds auth bypass, IDOR, and logic bugs Semgrep/CodeQL miss. Free GitHub Action. Supports Python, JS/TS, Go, PH

A browser game to learn prompt engineering by playing — explore a world and solve challenges by writing prompts. Techniques from OpenAI, Ant

Smriti (स्मृति): private, local-first agentic RAG with System 1 + System 2 thinking over your notes, books and documents. Guardrails, tracin

The first AI plugin that speaks first. Code-enforced learning + active forgetting + PAC (Proactive Accountability Challenge). Works with Cla

Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, a

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-

Find out which model actually answers your Codex requests (detects silent model substitution, e.g. gpt-6-astra served by gpt-5.6-luna)

Open-source Kanban where every column is an AI agent

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero

The execution safety layer for AI agents.

Multi-tenant LLM API gateway for Claude and Codex — single Go binary, USD wallet, Alipay top-up, per-token caps, status-page health, fumadoc

Open-source, local-first job search app for private discovery, evidence-backed fit scoring, truthful resume tailoring, durable workflows, an

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it te

把 OpenCode 的免费模型（big-pickle、LongCat、MiMo、Nemotron、Space Bunny 等）接进 DSH 的模型选择器，作为 opencode-xdbridge 分组使用，并在设置 → OpenCode-XD 里提供一个可视化的交互入口。

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

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

面向 AI 时代的数据可视化规范与工作流库 — specification & workflow library for AI-era data visualization

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

RigMark benchmarks local AI the way coding agents actually use it.

Agent skill for modern Android development with Jetpack Compose — best practices for code generation and review

A desktop coding workspace for AI agents — chat, files, editor, terminal, Git worktrees and browser preview, plus bounded, evidence-driven R

Practical Agent Skills. Install with npx skills add.

Yao 的开源小工具集合：聚焦本地优先的 AI 编码、网页截图、视频转写、终端诊断和磁盘空间分析工作流。

CareerDesk: Your Personal Career Assistant

The database agent for Postgres and MySQL - Point it at PostgreSQL or MySQL and ask questions in plain English — schema exploration, query g

Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref