Go

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

A fake CLI agent for testing orchestration tooling — emits Claude-shaped hooks, MCP traffic, and stream-json without calling any LLM.

macOS menu bar + CLI that watches Claude Code session usage across multiple accounts and switches to whichever has server-side headroom. Local-first, no telemetry.

Agent-friendly CLI for Dida365 / TickTick

Topic-grained, layered memory layer for AI coding agents — local-first, MCP, single binary. Plug Claude Code / Cursor / Windsurf / Antigravity into persistent memory across sessions and machines.

Agent-native scheduling system for AI Agents

A gateway + skill letting Claude Code agents collaborate across machines

A loyal historian sits between you and the AI, quietly getting to know you — your personality, habits, interests, profession, thinking style, cultural taste, and even your food preferences — so the AI can serve you better over time.

Lightweight host monitoring agent that reports CPU/RAM/disk/OS metrics + version info from each tracked server to the ICLIC license authority over an HMAC-signed channel. Audit-friendly Go binary, runs as a systemd timer.

PostGrip Agent SDK for Go

A lightweight Go implementation of Claude Code's agent loop framework with streaming support, 14+ built-in tools, and multi-mode permission control.

Stock AI Agent

Git hook that captures AI agent coding sessions and generates visual diffs showing exactly what changed and why.

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

Agent Identity Management

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

Go TUI app + Claude Code plugin that gives Claude sessions a persistent canvas display panel. Multiple TUI windows stay in sync via a shared Unix socket daemon.

Atomic, build-gated developer tools for AI coding agents: type-checked refactors, semantic search, and verify→fix loops over MCP, CLI, and TUI.

Build a Go mini-version of openai/codex, session by session — each chapter ends with the upstream Rust source. Generated by the learn-repo-generator skill.

Build a Go mini-version of SWE-agent/mini-swe-agent — the 100-line AI coding agent that scores 74% on SWE-bench — chapter by chapter. Generated by the learn-repo-generator skill.

Small TUI coding agent in Go for any OpenAI-compatible endpoint. Built-in read/write/edit/bash/grep/web_fetch tools, sandboxed shell, SQLite session persistence.

Lightweight multi-tenant agentic runtime in one Go sidecar. Owns the LLM tool-use loop across Anthropic, OpenAI, and Ollama with native prompt-cache control, MCP tool dispatch, and per-tenant fairness. TypeScript and Python adapters over HTTP+SSE. Powers JobEmber.

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

Local-first, state-driven AI agent platform. Plan-review before execution, capability-gated tools, BYO LLM (Ollama / Anthropic / OpenAI). Tauri desktop + Go runtime.

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

Claude Code OpenTelemetry

Automated friction detector for developers. An MCP server that monitors file activity and terminal errors to trigger AI coaching interventions when you're stuck.

Build a Go mini-version of HKUDS/nanobot from scratch — 11 chapters, end-to-end integration, bilingual docs. Pedagogy by shareAI-lab/learn-claude-code.

Ai autonomous agent

Jidoka Agent Platform — Compiled AI, Reflex ROM, organ.Func

A system of cooperative, always-on AI agents that function as a software development team

Your own personal AI assistant.

A Go-native runtime for durable, steerable, event-driven AI agents

OpenHarness-Go 是一个基于 Go 语言开发的高性能、高可扩展的 AI Agent Harness 项目