Coding & Development

Inject a custom Anthropic User-Agent into OpenCode for Claude OAuth, token refresh, API calls, and key creation

Discover exposed AI infrastructure including LLMs, agents, and ML pipelines using curated OSINT dorks, queries, and reconnaissance tools.

⚙️ Define and compile AI coding rules, commands, and templates into workflows that work across multiple editors and agents.

基于 claude code 构建的 harness 工作流

macOS desktop app for managing parallel Claude Code sessions (Tauri + React)

Run Claw AI agents in the browser with a serverless WebContainers runtime, secure WASM sandboxing, and audit-ready policy controls

Build Silver Browser, an open-source AI-native Electron browser with Ghost agent, shell access, sub-agents, and built-in ad blocking

装上可易桌面端，把 AI 员工 + 工作流 + RPA + AI 运行基建 一起装进去 —— 几分钟开张。/One person. The output of an entire team. Install ClawYi Desktop and get AI agents, workflows, RPA, and all the AI infrastructure you need — up and running in minutes.

Agent-native Unreal Engine tooling through MCP

Vant: Durable AI memory + cold storage + runtime for agents, with generational evolution, stored passively via GitHub. Built for long-running autonomous sessions, using file based persistence.

Rust-native tools​ for building AI agents and managing LLM deployments.

Self-directed AI agents that work autonomously on software — including improving themselves. Multi-LLM, K8s-native, AI-operated open source.

Chrome DevTools for the Model Context Protocol. Inspect, profile, replay, and diff every MCP call your agent makes.

Blackmatter Claude - Claude Code integration with LSP, Zoekt, Codesearch, and MCP servers

Codex skill for generating, cutting out, validating, and applying reusable PNG assets

Enable AI agents to retain memory across sessions using persistent storage designed for continuous context retention.

An autonomous FastAPI service that wraps an OpenAI-compatible LLM with multi-tier memory, Docker-isolated tool execution, swarm inference, and biological-rhythm self-play.

Audit-ready OSS substrate for AI agents — inline guardrails, telemetry, LLM-as-judge, escalation. Apache-2.0.

An agentic memory system implemented as an MCP server

赣东学院信息工程学院科创部活动策划案生成与验收 Skill，支持框架起草、Word 策划案生成、水印、审计和渲染检查。A Codex skill for drafting, generating, auditing, and rendering official activity proposals for the GDU School of Information Engineering.

🛡️ Explore and test prompt injection techniques safely for AI applications, enhancing your skills in ethical hacking and digital security.

Enable system-level AI agents on Android devices with on-device LLMs, secure tool control, and a conversational shell replacing the launcher

Contextual continuity infrastructure for AI coding agents — semantic memory across sessions and org-mode knowledge bases. Pi extension + Gemini Embedding 2 + LanceDB.

Bring Your Agent, Start to Fight! The Open Platform for AI Agents, Workflows, Prompts, and Battles