GitHub Copilot GitHub / Microsoft

Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.

The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia.

Agentic Runtime

Get your repo ready for AI.

WordPress plugin development skills for AI coding agents — Claude Code, Gemini CLI, Cursor, Windsurf, Cline, Codex, Copilot, opencode, and more

Claude Code with Token-free Plan. A Claude Code build repaired from the source leaked from Anthropic's npm registry on 2026-03-31. A token-free plan forever,enioy!

Skill do Claude para escrever copy de alta conversao (landing pages, advertoriais, VSL) para trafego frio de Meta e Google Ads, em PT-BR.

Nahida AI Agent - A QQ bot powered by MiMo model with knowledge graph, memory system, and tool calling capabilities

Workflow-first, AI-ready iOS architecture with typed effects, manifests, SwiftUI/UIKit examples, and agent-safe code generation.

A Claude skill that turns a codebase into an explorable isometric diagram, with real data moving along the edges

Local shared memory and controlled workflows for AI coding agents.

A personal marketplace of AI-oriented plugins for the GitHub Copilot CLI.

Astrology MCP server & Agent Skill — birth charts, transits, synastry across Western, Vedic/Jyotish & Chinese BaZi. Deterministic zero-dependency Python engine. 18 MCP tools, 31 REST endpoints, ChatGPT Action. Free & self-hostable.

Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server

Evidence-first AI agent workbench for vendor API integrate & contract heal — real production edits, multi-lang surfaces, live PRs (not a runtime SDK).

Universal Context, Rules & Handoff Bridge for AI Coding Tools (Cursor, Copilot, Cline, Claude Code, Antigravity, MCP)

One Harness to rule them all, One Harness to prompt them, One Harness to sync them all, and in your codebase bind them.

claude-mem 增强版 — 补齐原版缺失的多项目隔离、用户指令注入、国内大模型适配，安装即用无需配置

VLESS — 100% on-device visual perception browser agent with zero data egress and checksum-gated PII detection. Built for SIH 2026.

OS-level safeguards layer for AI agent loops — runaway-kill, timeouts & resource limits so coding agents (Claude Code, Cursor, Codex, Antigravity) in YOLO mode can't burn tokens or freeze your Mac

Drop-in toolkit that gives AI coding agents persistent memory across sessions. Agent Skills, cross-session learning loop, and knowledge persistence. Zero dependencies, no backend.

Reliability layer for AI coding agents: shared memory that survives sessions, blast-radius checks before edits, verification gates after — one config for 10 tools, zero runtime deps.

A markdown-based memory system for AI agents — stop re-explaining and re-debugging across sessions and models.

The AI Agent Governance & Quality Engineering System.

Local-first personal AI assistant with worker/skill bus, Telegram channel, LM Studio/OpenAI/Anthropic providers. Self-hosted alternative for hackers who want full control of the pipeline.

Palette: observability, evals, replay, and gates for agent systems

Copilot draws, you explore. Both stay in sync.

Claude skill: protect any website from getting hacked. External health check, code security review, owner checklists, incident response, cloud & AI/LLM security (OWASP Top 10:2025, MITRE ATT&CK).

A GitHub-native protocol for verified AI work on neglected global problems.