#ai-agent

Build internal tools and AI agents in Go — or just download and run Claude / Codex / Gemini as a Slack + Telegram + web agent host. No copy-pasting. You own the code.

AI-native Lexical rich text editor. Edit, render, SSR, and AI agent protocol (LiteXML) — all from one schema. React 19, TypeScript, Vanilla Extract, ESM.

MCP server for AI agents to read, edit, inspect, and validate local HWPX documents.

From-zero terminal coding agent: a key-holding OpenAI-compatible routing backend + a thin client with ~285 skills, MCP connectors, and ask/plan/auto modes. No build step.

OpenCode plugin for autonomous dev loops, planning, and worktree sandbox environments.

DeployHQ CLI — deploy from your terminal, for humans and agents

Security scanner for AI agent skills and MCP servers. Detects secrets, CVEs, supply chain attacks, and prompt injection in SKILL.md files before they're installed. Pre-install gate for Claude Code, OpenClaw, PicoClaw, NanoBot, FamClaw, and CI/CD pipelines. Single Go binary, MIT licensed.

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.

Discord control plane for project-bound ACP agents. Kiro CLI by default, optional OMP, MCP policy, audit, usage, cron, and thread agents.

A curated, opinionated set of OpenCode plugins for spec-first, review-driven, safer agentic development.

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status line (industry-first Codex faux statusline), GitHub-style heatmap, multi-model cost analysis

Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to website traffic, user behavior, and performance data with schema discovery, server-side aggregation, and safe defaults that reduce data wrangling.

Official Go implementation of the UTCP

Verification runtime and execution observability for AI-generated web apps.

A lightweight all-in-one terminal with 20+ protocols — SSH, RDP, SFTP, databases and more. With a built-in autonomous AI Agent that plans and runs multi-turn shell commands.

Across 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.

A self-hosted browser console for Claude Code and ChatGPT Codex. Run AI sessions from any browser or phone — tool approvals, model selection, context management, session history — without leaving your own machine.

AIエージェントの設計意図を無視した暴走を0.5秒で止める、AI非依存の品質防御ツールキット。5レイヤーで「No Design / No Code」を強制し、構造的整合性を守ります。

Yet another coding agent harness, lightweight and written in go.

The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.

Let AI agents share your everyday, logged-in Chrome through a Skill + CLI — locally or across multiple machines.

Semantic code search for coding agents — search by meaning like grep, trace call graphs, find tests & blast radius. 100% local embeddings (ONNX/MLX), MCP server, plugins for Claude Code, OpenCode, Codex & Droid.

AI-native CWE (Common Weakness Enumeration) integration layer — Skills, Go SDK, CLI & MCP. Ship CVE/CWE tooling to SAST/DAST, vuln-management & AI agents.

Model-agnostic design knowledge base + skill system for AI coding agents (Korean-market-fluent)

Опис репозиторію не опубліковано.

An agent that takes a dead research repo and turns it into a callable pipeline component.

Embeddable chat widget for smooth-operator — a web component that speaks the schema-driven WebSocket protocol. Built with tsdown, dogfooded into Smoo AI.

Go AI Agent 框架 — Go 生态的 LangChain + LangGraph：ReAct / Plan-and-Execute / Reflection / ToT 多范式推理开箱即用，图编排与多 Agent 协作，A2A 协议，OpenTelemetry 可观测。对标字节 Eino。Hexagon 生态 L2 核心。

An experimental ReAct agent implemented in Go.

Agent detection definitions and lightweight utility