Coding & Development

OpenBat agent skills for Claude Code, Cursor, Copilot, and any Claude-compatible MCP client

Dotfiles for Coding Agent Configs with Skills etc. For Claude Code, Codex, Pi, OpenCode and Gemini Cli

FX settlement agent on Sera Protocol — 7 knowledge domains, 6 skills, 9 MCP tools wired to live Sera endpoints. Multi-host: OpenClaw, Hermes, NanoClaw, Claude, Cursor.

A highly opinionated set of agents, skills, hooks, rules and tools for CLI coding agents like OpenCode, GitHub Copilot CLI, Claude Code, Codex, Gemini CLI and Factory Droid.

Universal context orchestrator for AI coding agents. Manage skills, memory, and rules across Claude Code, Cursor, Copilot, Windsurf, Gemini, Codex, Cline, and 15 more tools from one local dashboard. Zero dependencies.

Link skills, MCP servers, and AGENTS.md across Claude Code, Codex, Cursor, Gemini CLI, and OpenCode from one .agents/ directory.

Recently updated agent skill repository for ihorponom/agentpack.

Local flight recorder for AI browser agents. Debug Browser Use, Stagehand, Skyvern, and Playwright + LLM runs with screenshots, model I/O, and failure timelines.

Self-host secrets manager with an AI-safety layer. Aliases instead of values; AI agents never see real credentials. Cloud option coming.

🤖 A self-hosted Discord bot powered by an LLM with tool calling & per-channel context

Universal MCP Sync (usync) is a local-first MCP configuration manager for developers who use multiple AI clients.

LLM councils plan it. Ralph loops recover it. OpenCode worktrees ship it.

The Open Source Agent Harness Framework. Any LLM. Any platform. Agentic Programming Paradigm. ♾️

Costea: Know the Cost Before You Run Your Agents(OpenClaw, Claude Code & Codex...)

Pit AI coding agents against the same bug. Score them on tests, diff, cost, and time — pick the winning patch.

🤖 Native AI agent for your terminal and macOS desktop. Run cloud and local AI models through one secure runtime.

The tool-calling loop for LLM agents; iterator-first, protocol-hooked, one dependency.

A composite ai framework for agentic AI

HotPlex — Unified access layer for AI Coding Agent.

Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.

🔐 The password manager for terminal users and AI agents. Age-encrypted, keyring-cached, MCP-ready. Zero telemetry.

Trusted context for AI agents

Connect any LLM to OpenClaw — production-tested middleware for Qwen3-235B and beyond

AI Coding Agent