CodexBridge
WeChat-to-Codex bridge for running Codex app-server from chat, with threads, slash commands, approvals, agents, automation, uploads, and assistant records.
WeChat-to-Codex bridge for running Codex app-server from chat, with threads, slash commands, approvals, agents, automation, uploads, and assistant records.
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.
Chat with your data - with memory, rules, and observability built in. Deploy in 2 minutes
Local-first AI agents with governed, approval-gated memory. Any model provider; MCP tools and web search built in. Nothing remembered without your say-so, nothing leaves your machine.
An autonomous HR agent that can answer user queries using tools
Open reimplementation of Sakana Fugu — the 'one model to command them all' LLM orchestrator. Read → run → train → serve.
`agent-spec` is an AI-native BDD/spec verification tool for task execution.
AI agent tooling for data engineering workflows.
An open-source game coding agent environment and benchmark for Godot.
Plinth is an AI-native engineering toolkit for modern Java enterprise SDLC, built around reusable Commands, Agents, Skills, and MCP Servers.
A beautiful, zero-dependency command center for OpenClaw AI agents
RedFoxHub skill collection: a reusable set of SKILLs for agents, covering inspiration, topic selection, copywriting, and data review, continuously updated.
Vynaro (Xuying AI): a next-generation, fully automated 7-step AI video narration and first-person video creation tool, built with Tauri 2, Rust, and React 19.
Aurora — Open source AI-powered agentic incident management & root cause analysis for SREs. LangGraph agents investigate across AWS, Azure, GCP, Kubernetes. Integrates with PagerDuty, Datadog, Grafana, Slack and More. Apache 2.0.
Generate full-background Anthropic-style editorial illustrations with verified palette and hand-drawn visual rules.
Companionship, chat, coding and work share one memory and context framework, the kind of AI from science fiction that keeps you company and gets things done with you. A diversified agent project built on context and attention mechanisms.
An Agent Skill from programmer Yupi: distills himself into an AI skill pack that answers questions on programming learning, job interviews, AI coding, resume optimization, tech stack choices and entrepreneurship in his own thinking style and voice. Works with Claude Code, Cursor and OpenClaw.
An open SDK for agentic payments. Let AI agents make payments, hold funds, and move money across chains with policy enforcement and human approval built in.
The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.
Run Claude Code, Codex, and other agent CLIs in Obsidian
Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.
PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.
HomeGenie: The Programmable Intelligence with 100% Local Agentic AI.
Registry of agents implementing the Agent Client Protocol (ACP)