Havuz

A pure-Python reachability and skeletonization layer that decides what a coding agent actually sees before a request reaches the API.

Open-source terminal AI coding-agent harness for studying agent loops, tools, MCP, skills, safety, and persistence.

Zotero MCP server: search, citations, add by DOI, safe writes, semantic search and PDF page images for Claude, ChatGPT and any MCP client. T

discover LLMs punching above their weight

小liu破甲 - Codex CLI jailbreak prompt and one-click deploy tool. 基于CTF框架的Codex破甲提示词与一键部署工具

GoBuildWP (formerly WPPilot): WordPress MCP server & AI agent for ChatGPT, Claude, Cursor, Codex. Build and edit full websites in Elementor

Unofficial Google-Health-CLI for the Google Health API, written in Go

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

Zero-token, on-device vision for AI agents — OCR, pixel-exact UI targeting, and face grouping on Apple Vision. Pure Swift, single binary, no

Lightweight agent multiplexer, all in one Web dashboard

Self hosted Wiki + Jira-style AI native issue tracker on Cloudflare Workers

Agent skills that help you publish in the AER faster — identification-first empirics, AEA-compliant replication, Keith-Head intros, R&R rebu

KIPRIS 특허·실용신안·상표·디자인 검색 MCP — 자유검색/항목검색/출원인/권리자/서지상세 7개 도구 | KIPRIS Korean patent·utility·trademark·design search → 7 MCP tools

deptrust is a CLI that checks package versions for known vulnerabilities across npm, PyPI, crates.io, Go modules, RubyGems, NuGet, Maven, Pa

An educational macOS app: build and chat with a tiny language model, trained on your Mac

An LLM-friendly, single-binary, drop-in replacement to Supabase

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Manage OpenClaw in your team (Enterprise) by providing it compute infrastructure, tool integration, Authentication and security primitives

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, sessi

Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails

Hermes Agent skill for grading SOUL.md identity files with a research-backed rubric and public-safe field guide.

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

⚔️ Compare AI models side by side — same prompt, streamed answers, live code previews, speed, tokens and cost. Keys never leave your browser

Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP interfaces. Python, MIT.

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on

一款跨平台智能笔记 Agent 应用，支持多格式笔记、本地知识库、AI 智能助手、向量语义检索 。

ast-outline lets AI coding agents pull exactly the code context they need — a repo skeleton, a file outline, or one symbol — instead of read

Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP

Visualize your project's feature logic as a semantic flow graph — not call graphs, not import maps. AI writes the data, you see the story.

LemonClaw, an open-source, universal AI digital employee agent

42 AI agent skills for literature review, academic writing, citation verification, conference submission, rebuttal, publication, and present

One window for a whole swarm of AI coding agents — split terminals, per-agent git worktrees, live web previews, and a War Room where agents

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Go

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and ve

Git-native context control plane for AI coding agents

ICA Lens: compact ICA-based interpretability tools for exploring LLM activations. Code release for the paper.

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

AI 生成原生可编辑 PPTX 的 Skill：Claude Code/Codex/Cursor 一句话出 PPT，形状文字都能直接改｜AI PowerPoint generator (editable .pptx)

Multi-Provider AI Gateway, "Because we have LiteLLM at home" No personal logs by design. Model autodiscovery, Failover groups, High availabi

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

Security-first AI-native C5 teamserver (Command · Control · Cognitive · Collaborative · Coordination) for authorized red team & pentest. Bui

Wiki built using Karpathy method containing information about TPU performance optimizations and hooking it up to autoresearch optimization e

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

Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kern

讓 AI 用台灣人的繁體中文講話，並把已寫好的文字清掉 AI 味。Claude Code、claude.ai、ChatGPT Codex 與一般聊天都能用。

让你的agent真的像你一样操控你的浏览器窗口

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segreg

An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every c