Go

Turn documents into AI-ready Markdown with visual understanding

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Offline-first Go CLI for summarizing local token usage and estimated USD costs from Claude Code, Codex, and Gemini CLI.

Portable Claude Code dev environment in a Docker container — multi-session, hook-driven, web-managed, with transparent SOCKS5. Runs on a Raspberry Pi.

fak — the Fused Agent Kernel: one Go binary that turns a tool-using agent (Claude Code, Codex, Cursor, any OpenAI/Anthropic/MCP client) into a managed agent: cache-stable model traffic, context compaction + crash resume, nanosecond tool-call policy, local GGUF serving with SSD expert offload.

Setup for Agent Computers

Not just an agent demo — a local coding-agent platform: plan mode, sub-agent teams, cron, memory, MCP. Single Go binary, DeepSeek-native, MIT.

A simple MacOS helper for safer exposure of secrets to your agents

Cross-host development orchestrator for Codex CLI and Claude Code CLI

Your personal GitHub registry for AI Agent Skills. One repo. EVERY agent. EVERY device. Loaded on demand — Zero startup bloat.

GameAgentEngine is a Go-based engine that sits between your game logic and LLM capabilities — responsible for world modeling, NPC intelligent behavior, memory management, and world timeline progression. Think of it as the director system and intelligence layer inside a game world.

A live, read-only TUI monitor for AI coding agents (Claude Code, Codex CLI, Cursor) and their contexts — cards per session, not a resource monitor.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

The self-improving SRE agent

Reachability triage for vulnerability scans. Feeds scanner findings to an LLM agent that reads your source and decides which CVEs are actually reachable.

Tools and daemons for Claude Code (memory sync, etc.)

Your AI coding agents, in your pocket — monitor and manage Claude Code, Codex, and OpenCode from your phone or browser.

多上游、多协议转换的 LLM 代理网关

Terminal cockpit for running a fleet of Claude Code sessions across all your repos — dispatch work, watch what ships, and act on what's blocked, from one screen.

Multi-repo code knowledge graphs for AI agents. Cross-repo linking, infrastructure topology, watcher-driven freshness.

Herdr plugin that streams workspace & agent telemetry to an endpoint you control — Go, single binary, privacy-first defaults

Graph-native multi-agent orchestrator that runs each DAG node as a claude -p subprocess on your Claude subscription (no API key).

Share a full Codex or Claude Code conversation as one link, then import it into a native local thread/session to continue.

Never hit a rate-limit again. Route Claude Code, Cursor & 40+ providers through the subscription you already pay for, cut 40-80% tokens (RTK), stay un-banned. Self-hosted LiteLLM / OpenRouter / 9router alternative — one Go binary, anti-ban + sovereign P2P mesh.

Agent PR evidence — intent capture and session evidence rendered as a card on pull requests

Agent loop optimized browser use cli

Agent-friendly CLI for Dida365 / TickTick

Sleek, fast, token-efficient AI coding agent. Multi-provider (Cortex, OpenAI, Anthropic, Ollama) with a polished terminal UI. Fork of vix.

Canary — local Interactive Brokers MCP server, CLI, and risk desk. Standard builds and MCP are read/preview-only; a separate opt-in trading build provides gated CLI broker writes.

MCP-сервер для интеграции ИИ-ассистентов с 1С:Напарник (code.1c.ai) — проверка, ревью, генерация, редактирование кода 1С, поиск по ИТС/БСП/конфигурациям, консультации.

One open A2A 1.0 mesh for Claude Code, Codex, Cursor, Cline, Continue and Gemini.

Deterministic fake of the claude and codex CLIs. Test hooks and orchestrator integrations locally and in CI without an API key.

Agent Native CLI for publishing Markdown to X Articles with DraftJS, media upload, and OAuth2 PKCE.

基于 llama.cpp 的本地大模型桌面客户端：可视化配置 Qwen3.8-27B 等 GGUF 模型参数，一键启动 OpenAI 兼容 API，内置模型下载与实时监控 | A user-friendly desktop GUI for llama.cpp — visually configure GGUF models like Qwen3.8-27B, launch a local OpenAI-compatible API in one click, with built-in model downloads and real-time monitoring.

Redis Vector Library (RedisVL) — the AI-native Golang client for Redis.

Open-source football management simulation played by AI agents through MCP and watched through a TUI console.

Collaborative AI memory for engineering teams - share context across Claude Code, Cursor, and teammates