Havuz

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), rever

NEWTON: Agentic Planning for Physically Grounded Video Generation

Keep your Mac awake on your terms. A native macOS menu-bar app with condition-based triggers, closed-display mode, and a headless-Mac toolki

Run your AI agents on machines you already own, as one private P2P mesh. OpenAI-compatible, sandboxed with Podman, signed reputation, no clo

MCP server + CLI that puts a real human in your coding agent's loop. It publishes work mid-task, a reviewer pins what's wrong and returns a

Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion ima

Memory that remembers the story not just the facts. File System Memory and Three layer sentence graph for AI agents -> Facts, Episodes, raw

Agent-native browser with fingerprint control and proxy support.

Turn your Claude Pro/Max subscription into an OpenAI-compatible API for your IDEs and devices — LAN auth, per-key quotas, response cache, di

A Codex skill that delegates work to ChatGPT on the web.

给 DeepSeek Harness 用的科研文献库插件：搜论文、带出处、审批入库、把笔记线索交给同会话其他插件。Academic research library for DSH — search, cite, approve imports, hand off notes.

Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP co

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

A lightweight CPU only memory approach with ranked retrieval. Simple, yet effective.

Open-source tools for AWS DevOps Agent - extend DevOps Agent with ready-to-use skills, custom agents, and other tools, for incident response

Lightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on

Learn how to get started using the GitHub Copilot app!

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model

A scrolling terminal multiplexer that tracks your AI coding agents.

smol is a smol agent

Codex-first Agent Skills library for premium frontend, website, motion, accessibility, QA, and handoff workflows.

Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harn

An open-source agent harness for software work.

Your private, searchable work timeline for macOS and local AI agents.

The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.

Observability platform for Digital Employee, providing real-time tracing, session insights, and cost analysis for multi-agent workflows

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and

Open-source TypeScript framework for building operational software used by humans and AI agents.

A visual manager for fleets of Claude Code, Codex and Muse agents — real terminals, agents that message each other, teams that run tickets o

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.

让 AI 编程助手（Cursor / Claude Code 等）能更好地编写 Minecraft 模组的完整工具包。

The Open Analytics design language as an agent skill: component recipes with type-checked source, token CSS, and a CLI. Works with Claude Co

Voice-driven multi-agent assistant — Realtime API + CLI runners + multi-channel orchestration.

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and

Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware tabl

TradingView MCP server: search indicators and strategies, fetch Pine Script source. Works with Claude Code, Claude Desktop and Cursor. No AP

Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.

Ten cooperating AI agents that turn long podcasts into short-form videos, automatically. Free and open source, runs on free AI providers.

OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and TOTP while keeping hidden plaint

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger,

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini

Simple Reviewer: a Codex skill for AI-assisted coding and Vibe Coding. Explain code, visualize workflows, and verify goals with evidence. |

Browse and manage local AI skills, MCP configs, plugins, and agent activity on macOS 14+.

Run agents like a company. AgentOS is the native control plane for OpenClaw — manage agents, tasks, models, context, approvals, and runtime

Open-source, model-independent Agent Skill for evidence-based software reconstruction with REA. Optional integration, portable installer, an

A CLAUDE.md built on Karpathy's principles and gstack, adding a verification harness and autonomous-loop rules for Claude Code.

Learn what AI skills are and how to design, structure, and use them in real-world agent systems.

Whip is an agent-native SSH mobile client, designed specifically for the Herdr multiplexer from day one