Havuz

The Hale programming language: general-purpose, native and memory-safe, from a five-line script to a dynamic distributed system. Less langua

SkillRoute by JEStats — local-first skill routing for coding agents, with ranked matches, confidence, and evidence over MCP.

Your agent team, on your machine. Open-source harness for multi-user Claude agents.

Declarative automation for repetitive steps in herdr

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

Memory layer for AI Agents and OpenClaw powered by Rust

OpenClaw plugin for persistent AI memory

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

Reusable AI tools for the Laravle AI SDK

Zero-Mem: Zero-Token Memory Operations for the pi coding agent (faithful reimplementation of arXiv:2607.29377)

Git-native shared memory for AI CLI agents

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

A massive, self-updating local archive of AI tools — 11,000+ agent skills, 240+ MCP servers, 2,200+ IDE rules (Cursor/Cline), and 30+ system

CVE ingestion + enrichment pipeline with an MCP server for AI agents.

From Agent to Agency — 一个 AI 做不了的事，一群 AI 可以。Multi-Agent Collaboration Platform.

"Does this actually work with my agent?" An open, versioned registry of AI-agent artifacts: skills, plugins, MCP servers, models, etc. with

Machining process planning for motor shafts - input shaft geometry, RAG-grounded operations, machine tools, cutting tools, heat treatment, e

An AI agent for your desktop and terminal.

🧠 A council of AI models for the decisions that aren't no-brainers — they answer in parallel, debate to consensus, or get judged to a ver

Distributed, objective-led control plane for Lean 4 formalization projects.

Cyber Threat Intelligence Skills for each stage of the CTI Lifecycle.

One Layer, All Seekable

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

credential isolation for AI agents. Agents never see real API keys - structural guarantee, not policy.

MCP server for the tastytrade open API: quotes, positions, balances, and dry-run-gated order flow for LLM agents.

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

Agent Skills official site

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

Drop-in replacement for PostgreSQL with surgical, dependency-aware undo of transactions. Makes incident recovery zero-cortisol.

Cross-harness communication mesh for LLM agents, with rooms, direct messages, presence and visibility over TCP and no filesystem dependencie

Official code for the paper: "Multi-User Large Language Model Agents"

TERSE - a hierarchical state language for humans and AI agents.

CLI for discovering local skills and agent profiles and installing them across coding clients through format adapters.

Geode provides agents remote access to your Obsidian vault.

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

Self-hosted web UI for running Claude Code agents (with optional Codex support). Multi-session chat, voice, skills, social media, telephony.

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

Benchmarking headless browsers as agent runtimes

Nausicaa treats an Agent run as a dynamic topology of Lanes rather than one fixed linear loop. The model can decide when to observe, fan out

The open-source talent graph for humans and AI agents.

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

How to start and best practices wuth AI for programmers and non-programmers

LEGO Design Agent

一款专注于慢性病管理的AI平台，通过多Agent协作问答、干预效果仿真预测、认知评估与训练、亲情账号关怀等核心技术，为慢病患者提供专业、个性化的健康管理服务

Mission control for every Claude Code session on your machine.

Cost saving Cognitive Architecture for AI Agents. Infinite Context. Perfect Recall. Zero Hallucinations.

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