Havuz

Git-native context control plane for AI coding agents

《从0开始构建 AI 智能体》 一本带你亲手打造属于自己的AI Agent 的实战书

A traceable personal memory layer that carries verified state across apps, models, and AI agents.

A desktop workspace for crafting vivid AI personas and exploring what emerges when different personalities fuse.

Nexus — execution infrastructure for AI agents. Host agents in the cloud or behind NAT; let users attach and authorize their own computers a

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop

An end-to-end encrypted channel between coding agents, anywhere

Scan your home, turn it into a live 3D model, and make it your TV's home screen — lights wired in. An AI-agent playbook + reference implemen

Design-system and vocabulary drift, enforced. Tailwind themes become law, rogue values get receipts, words live in a database agents inherit

Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

GitHub Issues-backed agent orchestration for Claude Code – a single Claude wears persona hats (Orchestrator, CEO, workers) routed by issue l

Multi-agent orchestration & workflow engine. Declarative YAML workflows, LLM coordinator with hub-and-spoke mailboxes, race-safe delivery. O

Free, AI PR reviewer that runs entirely in GitHub Actions. No hosting required.

Open-source bilingual resume autofill agent for verified profile building, recruitment form completion, attachment preparation, and reviewed

The self-hosted, multi-tenant AI app builder for teams. Sandboxed, audit-logged, MIT-licensed. The open-source alternative to Multi-Tenant S

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embe

One GUI for native Claude Code, Codex, Cursor and more agents — manage them in one place, connect across devices. 一个 GUI，接入原生 Claude Code、Co

Decision-first dashboard compiler and governance layer: decide whether a dashboard should exist, enforce evidence-backed semantics, and veri

AutoResearch + PromptFoo = AutoPrompter. Run it with Neo AI Engineer

Rust-first, local-first multi-agent runtime with a desktop HUD, policy-gated tools, voice, and worktree-isolated coding agents.

The AI study agent that learns how you learn — RL picks the action, FSRS picks the timing, the LLM only writes the quizzes. Chrome extension

Never keep an agent waiting. A free, open-source Mac menu bar app for Claude Code, Codex and Cursor: see which session needs you and answer

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep

Double-check before you ship: grill the requirements, test the implementation, prove the delivery. An engineering-discipline bundle for Deep

346 reusable character attributes for AI agent personas — compose, measure, and port system-prompt personas. Build once. Keep personality ev

两个配套的 Agent Skill：一个搭 harness，一个给 harness 体检。标准 SKILL.md 格式，Claude Code / Codex / Cursor / OpenClaw 通用，脚本也能直接当 CLI 跑。五层框架 + 可视化报告，破坏性动作一律先出方

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Serve clean Markdown from your Next.js site to AI agents, crawlers, and LLMs. Humans get HTML, agents get clean Markdown of the same pages.

Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

Mission control for long Claude Code runs: context and run progress at a glance, Autopilot handoffs, guardrails and a calm activity view, in

Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%

An AI coding harness that shaped itself - repo awareness, surgical edits, validation, recovery, and safe diff approvals.

Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase

💎 LaPis — Local AI memory for coding agents. Persistent SQLite memory for Pi, Claude Code, Hermes & MCP.

See which AI coding agent needs you — right in your tmux tab bar. A colored dot per window (working/blocked/idle) with off-screen sound aler

Spec-driven Claude Code, dropped into your repo in one command.

Production-grade AI agent memory and context management platform (monorepo)

Test copy, prices and emails on a panel of researched customer composites before real customers see them.

Open source Agentic Development Environment

🤖 LLM Engineering Roadmap — Complete Developer Guide

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

Durable Cloudflare computers for agents: run repos, steer live workspaces, verify results, and return receipts.

Give ChatGPT a real terminal on your Mac. Open-source MCP bridge for shell, files, PTY sessions, jobs, and Codex history.

Open GRC skills for AI agents. By ISMS Copilot.

controls the entropy of the codebase by enforcing code module boundaries.

AI agent tooling for Loxone Miniserver — natural language → config-as-code → deploy

A Claude Code skill that scaffolds ready-to-run LangChain Deep Agents and dcode CLI agents into any project.

Codex 三層多代理協作 Skill：Sol 統籌與複雜推理、Terra High／XHigh 處理視覺與操作、Luna Max 執行可重複工作。

Lightweight, local-first memory for AI agents. Hybrid vector + BM25 search, LLM-powered fact extraction, zero infrastructure — just pip inst