Havuz

ZeroSpec is a zero-dependency Markdown framework that helps AI agents understand your repository structure, rules, and source of truth befor

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

A local-first AI control plane for orchestrating agents, models, tools, and machines from one desktop app.

A locally-running multi-agent human in the loop system for deep, interdisciplinary research with only 4 dependencies.

Secure and scalable way to delegate work to AI agents from anywhere. Build a team of agents that work for you.

长任务执行 Skill：先定成功标准再逐轮验收，让 Claude Code/Codex 跑完长任务不半途而废｜Goal-driven long-running agent tasks

hSUM: Stateful Understanding & Memory — local evidence for agents. Keep the source. Return the passage.

Hive Agents harnest agent loop localfirts

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at

Metarhia skills 🪄

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No

Open Source Data Science Agent for Discord and Slack

Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

A host-side, scriptable command-line terminal for Segger-RTT; Also the AI-ready command line for embedded validation.

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

10,000+ CLI tools. One CLI to access. Zero configuration

Clyro is a governance platform for AI agents. While most tools let you watch agents fail, Clyro stops failures before they happen, catching

Open-source AI agent platform for building, deploying, and managing AI teammates. Role-based agents (PM, Engineer, Support, Marketing) with

Official Repo for Spreadsheet-RL

Source-linked collection of published AI model benchmark scores.

AI Skills（ai-skills.ai）是一个面向各行各业的 AI 技能库。可直接用于openclaw，Hermes，qclaw，claude code，codex等智能体平台。为你的职业发展、行业竞争力，增加更多可能。

Open-source AI workspace for humans and agents — SuperCompress as the core context layer.

Semantic memory system with knowledge graph, spreading activation, embedding-based recall, autonomous dream consolidation, and C++ LSTM+kNN

Self-hosted 多用户 WeChat / 微信 AI 智能体控制台，支持 Web 管理、Docker部署、MCP、Skills、记忆、定时任务、沙盒执行和长期运行，支持分享AI Bot给团队成员。

TUI Music Player - now agent native!

A personal assistant you deploy, built on OpenComputer Serverless Agents

Kraivor is an AI-powered system that analyzes real-world codebases and simulates how they behave under production stress, failures, and scal

Vetix — Automated scanning, identification, and assessment of SKILL security risks, based on Golang.

Simple and composable logging for Swift apps, servers, and coding agents.

Evidence-driven skill evolution for Hermes Agent — reports, dry-run proposals, candidate search, and guarded apply

34 FinOps specialist AI agents + 6 named-pattern playbooks. Drop into Claude Code, Copilot, Cursor, Windsurf, Aider, Gemini CLI. MIT.

Single source of truth for AI coding agent configuration — skills, commands and rules shared across OpenCode and Pi.

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

Make your agents learn from experience. One protocol for weights, harness and routing.

AI coding agent with more freedom.

Desktop IDE for working with multiple AI coding agents. Supports Claude, Codex, OpenCode, Cursor and Grok.

Allen is an open-source AI engineering team that runs on your repos — specialist agents, deterministic orchestration through workflows, and

250+ real-world TypeScript AI projects: workflows, agents, and multi-agent systems with production-ready architecture, not chatbot demos.

A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

One command to cut token usage by up to 50%+

Open Travel AI Platform — domain-specific AI agent orchestration for the travel industry

A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.

PANews Agent Toolkit is PANews's official agent package for cryptocurrency and blockchain news discovery, creator workflows, and PANews web-

An MCP server for parallel browser automation by AI agents with multiple cloud providers

Write, validate, and review Agent SKILL.md's directly in Visual Studio Code. SKILL.md Inspector provides live diagnostics for every file na

Create & stream personalized agentic video briefings on any topic.

The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-