#gemini

Open-source AI Agent platform — 80+ MCP tools, 7 channels (Slack/Discord/LINE/Telegram), Rust + Python. Self-hostable Claude/GPT alternative for production multi-LLM systems.

Minimal LLM API reverse proxy for Claude Code, Codex CLI & Gemini CLI — YAML routing, hot reload, and automatic provider failover. 极简 LLM API 反向代理：面向 Claude Code / Codex CLI / Gemini CLI，支持 YAML 配置、多上游优先级与自动故障转移。

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

One CLI to manage AI agent plugins and skills — author once in a single manifest, adapt to Claude Code, Codex & Antigravity. Versioned & reproducible.

A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.

MCP server that wraps the Antigravity CLI (agy): run agy prompts and peer reviews as async, restart-resilient jobs over stdio or Streamable HTTP.

your orchestrator for all dev agents, sessions, and environments.

Todo and task management

Roblox Studio MCP server & plugin for Claude Code, Cursor, Codex, and Gemini. AI-powered scripts, terrain, assets, lighting, and bidirectional project sync.

For AI enthusiasts who try every new tool and watch their skills fragment. One source of truth for AI agent skills (SKILL.md) + cross-tool sync toolkit: MCP server, shared instructions, and one-command wiring for Claude Code, Codex, Gemini, Kimi, Cursor, Kilocode, OpenCode.

Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.

Switch between multiple Claude Code and Codex login accounts, locally and safely. A switcher, not a rotator.

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

No repository description published.

Contexer captures architecture decisions, constraints, conventions, and patterns from AI coding sessions. Replays them in next session so you don't have to explain it again. It works across multiple AI agents.

Local-first CLI for managing and switching multiple AI coding tool profiles

Search history local agents for prompts and conversations (Codex, Claude, Cursor, agy, grok, pi, opencode)

Query companion: Database co-pilot

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

Multi-agent GUI for AI coding assistants — Claude Code, Gemini CLI, OpenCode & more. npx agentgui

Build an agent in a few lines: MCP + agent skills + native + HTTP tools, one interface, any LLM. JS/Python/Go.

An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.

Production-grade Harness Engineering Framework for multi-developer AI coding agents — guardrails, state persistence, direction alignment, and self-correction across 6 IDEs. Zero dependencies.

Ask your repo what breaks before an AI coding agent edits it.

Convert AI-generated Markdown to WhatsApp, Telegram, Discord, Slack and Instagram compatible formats using an Intermediate Representation (IR) in PHP.

Get a saved, cited report from your AI agent

Agent plugins and MCP to empower LLM to perform reliable sprint driven developement

Predict rate-limit cutoffs inside your AI agent. Local MCP server + CLI that tracks Claude Max, ChatGPT Plus/Pro/Team, GitHub Copilot, Cursor plan windows and warns before you hit the cap.

Local-first LLM token counter: exact OpenAI BPE, Claude/Gemini estimates, context-window usage. Zero network. CLI + Go library.

AI for the Command Line