Havuz

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif

Personal-Model First Self Evolving AI Agent 🐘

Open-source adversary emulation for AI agents and MCP servers.

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

Inference-native Tokenmaxxing Agent Harness for Loop Engineering

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence

The open-source operating system for physical AI.

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Cal

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

《推荐系统：工业架构与核心算法》开源书稿

Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysi

Deterministic safety solutions for probabilistic AI agents

Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives

The ADE for AI agents. Automate everything else. Do your true work.

Local editor for importing, managing, running, and injecting APM-backed assistant packages.

Vigil SOC: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.

Open-source AI office assistant for your desktop: describe the result or file you want in one sentence, and Abu plans and does the rest. Loc

An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, a

Outworked - Cozy Office for Claude Code

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

The one place for the skills, keys and memory of every agent you use. Formerly OMNI.

A native macOS terminal app built on Ghostty for running and supervising coding agents

AI-powered Vibe Investing for NASDAQ, S&P500 & crypto: LLM quant trading tools, multi-agent backtesting, and data-driven market columns (mNA

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, c

A curated list of code samples and tutorials for building agents on Gemini Enterprise Agent Platform (previously Vertex AI).

From ticket to reviewed pull request. Free and open-source, on your machine.

Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language. Works with Claude Code, Cu

A native macOS terminal for agent-driven development, built on Ghostty.

An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 1

A local-first, cross-platform Electron desktop workspace for Pi Coding Agent, with sessions, project files, browser tools, skills, plugins,

The graph based agentic IDE

A practical collection of plug-and-play starter blueprints for building autonomous AI apps with real APIs. Discover ready-to-build agent wor

Unified Agentic AI and Data Platform

Robinhood Agentic Trading agent — a fully automated AI trading bot placing real orders through Robinhood's Agentic Trading MCP, under mechan

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinfo

Autonomous, headless Android debugger designed for AI coding agents. Inspect runtime memory, set breakpoints, and debug live apps.

本地优先的 AI 投资研究工作台（AI investment research workbench），支持深度调研、证据化投资论点、投资组合风险分析、自选股与 Pi Agent 副驾驶。

Kane CLI by TestMu AI (Formerly LambdaTest)

Turn your Win, Mac or DGX Spark into an AI hotspot. Nightshift races hundreds of attempts overnight and keeps what passes. Plus the open con

Poirot is a deep research agent kernel built for those who care about how agents are architected.

An agent design team you control: 10 agents that run an inclusive design process while you direct.

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimizati

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil

AI Developer for Unreal Engine — An autonomous AI agent that creates Blueprints, C++, levels, materials, widgets, and more inside the UE5 ed

A deterministic privacy boundary between your data and AI.