Havuz

Search & apply to ~4,700 salary-transparent tech jobs across 7 countries (🇨🇭🇩🇪🇬🇧🇺🇸🇨🇦🇳🇱🇫🇷) from your terminal or AI agent — zero-dependency P

Run your own AI team from your phone. Claude Code, Codex and more on your own server: shared tasks, always-on agents, a small composable bas

Turn Android Termux into an autonomous AI agent and security orchestrator. Powered by a local ReAct framework with 50 system tools and MCP s

Put Claude Code, Cursor, Codex, Gemini & Antigravity in one room — real-time multi-agent AI collaboration over MCP for distributed dev, code

Remote coding harness exposed as a secure Streamable HTTP MCP server

The $0 AI Empire Playbook — 180 scheduled jobs, 43 free LLM lanes, and the failure classes that almost killed it. Free tiers only.

[ICML 2026] AutoControl Arena: Frontier AI Risk Auto-Discovery Platform

Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.

Turn npm, Python, and Rust release evidence into bounded Codex maintenance tasks.

Self-hosted AI Agent Memory + Code Intelligence Platform — one MCP endpoint for persistent memory, AST-aware code search, shared knowledge,

自托管 AI Coding Agent（Rust）：常驻 Runtime 撑起终端 / 浏览器 / 手机三端；每行改动可追溯到具体 Agent 与工具调用，子 Agent 的活由退出码裁决，检查点回退、目标 token 预算与验收清单跨轮次跨重启累计，用量与反馈账本留在本地。接任

Open-source starter stack for Agent product developers: desktop client, control plane, workers, multi-agent workflows, admin, mobile, and op

Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven,

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

ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Stream

Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see y

面向 AI 上下文管理的 Agent Skill：为 Codex 上下文管理、Cursor 上下文切换和 Claude 上下文管理提供跨窗口续接，用 Git 保存可验证的功能说明与变更记录。AI coding context management and agent handof

Product-Driven Development for coding agents

Cheaper and better Greptile alternative runs on your own github actions.

Turn any AI agent into a research co-scientist: 280+ open-source agent skills for literature reviews, hypotheses, experimental design, data

ClawMax is OpenClaw to the Max! 🚀 A web orchestration layer for OpenClaw agents, teams, workflows, and templates.

A universal scaffold for AI-assisted game development. 42 agents, 51 commands, 86 skills. Multi-engine (Unity, Unreal, Godot, HTML). Multi-h

the governed runtime for agent skill workflows, off the leash but on the record

VetarAI 是一款全原生 Swift 的本地桌面应用：多 Agent 协作、可视化工作流、拉模式知识仓库+本地语义检索、多模型超级工作室、CU 电脑操作。数据保存在本地磁盘。

Agentic AI platform with pixel agent technology — autonomous code generation, PR automation & multi-tenant SaaS

Open-source research assistant and MCP audit toolkit for systematic reviews: cited research reports, PRISMA tracking, evidence and claim che

Architecture Deep Research: deep research for strategic system design decisions.

Local-first raster-to-vector desktop app. PNG/JPEG/BMP to SVG/EPS/DXF/PDF/PNG. No account, no credits, no subscription — offline by default,

AI-powered exam question generator. Upload study materials, get exam questions in seconds. Open source, local-first, cross-platform.

SDK, skills, and examples for Inkbox: give AI agents a persistent identity with email, phone number, and internet address

Local-first persistent memory for OpenAI Codex: governed recall, progressive disclosure, no hosted vector database.

基于 Spring AI 2.0 的生产级 ERP 智能助手｜Production-ready ERP AI assistant with RAG, Tool Calling, chat memory, dynamic SQL tools, multi-tenancy and E

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit sever

See and manage what your coding assistants load — skills, commands, subagents, plugins and MCP servers, with real usage.

Let agents control many desktop software directly from the cli, with one pip install, and no MCP servers.

Self-evolving agentic reward framework for image-editing evaluation — 47.4% on EditReward-Bench from only 100 preference demos, no reward-mo

面向个人的本地多 Agent 协同工作空间。与拥有独立身份与持久记忆的 AI 队友深度协作：频道分工、任务指派、无限矢量画布与原生 MCP。A local-first multi-agent collaborative workspace.

A task board and Agent system inside Codex Desktop. Local-first, open source, macOS and Windows.

Reusable GitHub Action that reviews Terraform PRs for security, cost, and style using a LangGraph multi-agent system, posting a single sever

Re-anchor long conversations that drift through repeated local corrections.

GitX is a portable AI-agent skill for creating clean Git commits, tagged branches, and safe pushes across Codex, Claude Code, Cursor, and ot

Native VNC, RDP and SSH client for Windows, macOS and Linux. Pure-Rust protocol cores, Tauri 2. One host library for all three, plus an MCP

Your brain, then your team's brain, then your agents' brain. Drop in documents and it compounds them into an interlinked markdown wiki you o

Amplify yourself and your team – with AI co-workers.

Build your own Company OS with Claude Code. CLAUDE.md template, 5 GTM skills, workflow plugin, safety hooks, and full blueprint.

An AI-assisted newsroom workflow system for event tracking, evidence organization, approval chains, correction handling, and post-publicatio

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

Agentic DFIR

Self-hosted AI agent runtime — personal assistants, autonomous workers, and everything in between. Built on the Claude Agent SDK.

可扩展到各个领域的多 Agent 协作平台：自动分析任务，动态组建由不同角色组成的 AI 团队，协同完成复杂任务。