Havuz

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

GUI configuration manager for Kiro CLI — agents, MCP servers, steering, skills, and workspaces

Agent skill that helps Claude Code, Codex, Gemini, and Cursor write correct Swift App Intents code for Siri, Shortcuts, Spotlight, widgets,

An agent skill for deploying, operating, and automating workloads on Northflank. Includes guidance and references for services, jobs, addons

Save your GPT-6 Astra tokens. Let Luna do the dirty work.

An AI agent for your desktop and terminal.

A lightweight implementation of an orchestrated multi-agent workflow, in which a central coordinator delegates tasks to specialized subagent

Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as str

PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents

Understanding CLAUDE.md, MEMORY.md, SKILLS.md, SOUL.md, and Related Prompting Mechanisms

Fast hybrid code search for agents. Pure Go, drop-in MCP-compatible with semble.

Mission control for every Claude Code session on your machine.

Declaratively deploy & manage multiple isolated AI agents on a single NixOS machine — each with its own secrets, skills, and personality.

Type-aware, evidence-backed delivery contract for AI coding harnesses. Different agents in. One predictable human handoff out.

Mod your favourite games without writing code. Modmixer is a desktop app that decompiles/indexes your game and provides your AI coding LLM (

AI-native, source-available (PolyForm Perimeter) game-dev toolkit: bforge — deterministic headless-Blender asset forge for AI agents (138 op

Tandem lets you connect and control any coding agent—including Claude, Codex, or Hermes—across different devices. It allows all your agents

Karpathy's autoresearch loop, applied to outbound. Agent-operated GTM that scores replies AND silent self-serve across email, LinkedIn, and

An opinionated agent command center for extreme productivity. Runs on localhost.

One command turns every agent session already on your disk into a graph: subagents, tool calls, retries, the moments you said no. Ask your a

Skills, commands, and integrations for AI coding agents.

🧠 Community skill for Claude Code & Codex that helps your agent learn from its mistakes. /aprende reviews the conversation, surfaces durable

No Mac Mini? No problem. HermesFace is the best free way to deploy Hermes Agent on HuggingFace Spaces — 2 vCPU, 16GB RAM, 50GB storage, alwa

Teaching people about WebMCP

The agent that evolves with you 𖤍

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an

Open-source visual ai builder that lets you design AI visual ai agents workflows by dragging and dropping nodes on a canvas, and then compil

Claude Code skill inspired by The Grug Brained Developer

Record-and-replay for agent decision graphs: reproduce a prod agent failure as a committed regression test, and re-run your fix without live

Visual testing for agents: uiverify CLI, Vitest/Playwright SDKs, and agent skills.

The autonomous pentester that proves its findings — AI-driven, evidence-first, behind-login.

Open-source AI vulnerability discovery

AI agents are increasingly given real-world power — moving money, executing trades, taking actions with no human in the loop. But autonomy w

Embedded long-term memory database for AI agents & LLM apps. Six-layer cognitive architecture, knowledge graph, hybrid BM25 + vector search,

A living AI civilisation you can watch: tiny creatures discover, build, teach and pass knowledge on, with any LLM in their minds.

Red Team + Blue Team agents for Claude Code. Automated security auditing with ~100 lines of Markdown each.

Reference harness for the Big Finance benchmark of workflow-grounded financial-research questions

Lighthouse for agents - score an agent run, then tell it how to get faster and cheaper.

Universal OpenCode TUI sidebar for browsing provider agents and subagents

Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.

Praxis Policy Engine (PPE)

Official implementation of “ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation”

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

Evolving what multimodal agents see and how they read it. Framework, ten reusable task skills, and paper resources.

CounterStrikeSharp plugin for CS2 weapon skins, knives, gloves, and agents.

Native compact Nix build output with full local logs, bounded diagnostics, and a flake interface

Pi Skill Orchestrator is a Pi extension for people who use a lot of Agent Skills. It keeps Pi's normal skill autocomplete, but it stops the

CAP plugin to build agents

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

Extracts claims from SOPs, policies and regulations, has a person approve or reject each one, then serves the approved set to agents over MC