Havuz

Open-source privacy firewall for AI agents: masks personal data in text, tool calls and images before it reaches the LLM, and restores it in

Claude Code plugin: a supervisor plus specialist AI agents, an Opus review gate on all code, saved reports and a Team Board

Self-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero se

Open-source, agent-first GitHub and GitHub Actions alternative that runs on your own Cloudflare account: git hosting, pull requests, code re

SOC, incident response and SecOps for Linux servers in one agent: learns each host, watches it with zero-token sensors, triages with a small

Micro-VM sandbox for AI agents: isolated, gated and auditable, to prove what your agents did

Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.

Clear work. Reliable handoffs. An open-source agent skill for dependency-aware ticket coordination, shared HTML tracking, and durable recove

FALSIFY · 证伪 — 先证伪，再决定。A portable reasoning kernel: evidence layering, falsifiers, and a tamper-evident forecast ledger for any AI agent.

Less hype. Better harnesses. Measurable outcomes. AI Agent 思考与实践：上下文、工具、评估与超越拟人的设计。

A code-only world engine for AI agents: build whole towns and landscapes in three.js as code (pre-alpha)

Find scholarships you can actually win: eligibility checks, fit scores, missing papers and a dated plan. 35 scholarships + 56 Erasmus Mundus

MatOS: an agent operating system for materials research, with a layered scientific asset graph, stateful adaptive workflows and evidence-dri

Install an AI software factory into any project: a spec-driven pipeline for Claude Code, Codex, Cursor and Gemini, for developers, designers

BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI.

Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, an

Pixel-art diorama playbook and Three.js code kit: research-first build workflow, locked camera, palette snap, ordered dither, inked contour,

A privacy-first local coding agent that consults frontier AI models without exposing your source code.

Describe a thing, get a hologram, a 3D model and its parts: built by any AI agent, honestly.

Instant messaging between coding agent sessions — Claude Code, Codex, opencode, Cursor CLI, MiniMax Code and ZCode — across tools, to other

Finds the corrections you keep repeating to Claude Code and turns them into evidence-backed CLAUDE.md rules. Local CLI, no LLM by default, p

Fastest cross-platform E2E Automation for Mobile & Web

A drop-in AGENTS.md system prompt for coding agents: full execution, no hedging, no moralizing, no fade-to-black.

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind

Agent Skill that lets Claude Code, Codex, Cursor, Copilot and other AI agents set up and harden a Debian/Ubuntu VPS without locking you out:

A Mac browser on WebKit, not another Chromium, that still runs Chrome extensions. Arc-style Spaces, terminal tabs, and a built-in MCP server

Local-first desktop app for inspecting and safely managing the Skills, MCP servers, CLIs, and instruction files your AI agents use.

🔥🔥 Accelerating decision inference with exact state forking

让大肥鱼在 DSH 中长期生活：在B站社交、生活（未来扩展多平台），具有长期记忆、可塑造人格、自然好友关系

The game engine built for AI agents. Games are JSON, errors come with fixes, and agents play-test their own games headlessly.

Agent skill: multi-agent gather-and-verify pipeline for deep literature search — 20 sources, two-layer verification with saved evidence, rel

A 3D office that mirrors your Claude Code sessions; prompt, approve and follow them from any device over Tailscale.

Hermes, on the fly. A light, everyday mobile app (PWA) for your Hermes Agent bots.

Connect AI agents to real iPhones and Androids

A blazingly fast programmatic video engine, made for agents.

See what every Claude Code and Codex agent on your machine is doing — live, in a little office.

An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.

把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.

Let your AI agents call your phone over VoIP, and call them back. Your phone rings like a real call, even locked; a voice AI talks it throug

Native Windows Bash for AI coding agents. Run Claude Code, Codex, opencode & Gemini CLI without Git Bash, MSYS2 or WSL. Built in Rust, with

Agent skill: examine a product you're authorised to rebuild, build your own, then test against the original and fix gaps until every must-ha

Open-source AI alternative to Buffer and Opus Clip: Claude Code makes on-brand videos, posts them to 9 platforms and drafts replies. Self-ho

Rust framework for GPUI with native and browser apps, runtime inspection, and agent control.

Live trading arena for LLM agents: public reasoning, real market data, virtual capital

A honeypot and guestbook for AI agents that land on a machine they weren't invited to

Personal malleable interface. Everything is plugin. Ultrafast built on rust. Built for AI agents.

A WPF workspace for large images and whole-slide images, with layered annotations, MCP agent integration, and human-in-the-loop review.

Read-only Kubernetes troubleshooting skills for Claude Code, Codex, Gemini CLI and Copilot. Each one tested by an agent on a real kind clust

Review what your coding agent changed, without leaving Rex. Think herdr-reviewr, but for Rex.

A harness that lets AI agents make server-client games of commercial quality on a prebuilt core