Havuz

Agent Usage Detail Record — an open JSON standard for attributing and costing agent runs

AiGuard —— 本地优先的 AI 流量安全网关：本机 MITM 代理只接管 AI 域名，请求侧脱敏、响应侧流式还原，并识别七类风险信号。原文不落盘、不上传。（注意如果你需要模型直接使用token或者其他密钥进行操作，请放入白名单或关闭该功能！！！！）

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

Fast structured Android control loops with TypeSafe Jev and Mobile MCP

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

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

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

🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain

Control plane for swarms of sandboxed AI agents: run, fork, pause, steer, and checkpoint agents that each work inside their own isolated san

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。

Multi-agent coding factory made fast.

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

多agents协作平台

Geode provides agents remote access to your Obsidian vault.

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

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

A cross-platform agent framework and samples, support on Windows/MacOS/Android/iOS/HarmonyOS

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done cla

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

Internal agent platform on Amazon Bedrock AgentCore: interactive Claude Code cloud workspaces + headless agent kernels behind one portal, wi

a unix-like du command line tool to count token usage per files and directories

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

Mission control for every Claude Code session on your machine.

AI remembers, you find. File-based long-term memory and project maps for any AI coding tool, plus a zero-dependency governance CLI for chang

The agentic debugger for Claude Code, Codex CLI and Gemini CLI: a token usage, cost and context-window tracker that shows what the tokens AR

Give your coding agent a delivery process you can trust. Spec → Plan → Build → Acceptance → Ship.

Sentinel shows what a file would make your AI coding agent do. Static analyzer, merge gate and signed lockfile for CLAUDE.md, AGENTS.md, .cu

Is your CLI ready for AI agents? Automated checks to ensure optimum agentic CLI use: don't block agents, don't waste tokens, ensure safe use

Turn internet-scale video into egocentric and exocentric training data, curated and annotated by agents on the Memories.ai datalake

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

A minimal, explicit, provider-safe harness for the Pi coding agent

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

Open-source IDE for Claude Code. Multi-project workspace with chat, terminals, and git worktree management — all in your browser.

Self-hosted CI Fix. When CI breaks, your coding agent opens a Fix. Optional promote and revert. MIT. Nothing phones home.

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

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

Hive Agents harnest agent loop localfirts

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

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

A statistical code analyzer built from your repository's history.

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

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

Metarhia skills 🪄

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

Agree on a program. Run it together. Verify what happened. Wasm + p2p + state machines + verifiability

Self-hosted collaborative knowledge system for organizations.

🌐 Persistent 3D/2D spatial world model MCP server for AI agents. Entity tracking, object permanence, AABB collision simulation & view frustu

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

Reusable AI tools for the Laravle AI SDK

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