Context7
Up-to-date docs for AI agents
제작자가 쓴 설명(영어 원문)
Context engineering for AI coding agents: product context, project missions, and 360 memory.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://app.giljo.ai/mcp터미널에서 이 명령어를 실행하세요
claude mcp add --transport http hq https://app.giljo.ai/mcp프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"hq": {
"url": "https://app.giljo.ai/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"hq": {
"type": "http",
"url": "https://app.giljo.ai/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://app.giljo.ai/mcp메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
서버가 도구 목록을 보여 주기 전에 로그인을 요구해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리 이름이 도메인 giljo.ai 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
168ms 만에 응답(HTTP 401)
OAuth 로그인을 지원한다고 밝혀서, AI 앱이 로그인 화면으로 안내해 줘요
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 3개 중 3개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(2.13.0)은 3일 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: Context7, Codebase Memory, Exa
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Context engineering platform for AI-assisted software development.
Define your product once. Every agent that connects gets the full picture.
Free Community Edition · Self-Hosted · Privacy First · Bring Your Own AI
Works with: Claude Code CLI · Claude.ai / Desktop · Codex CLI · ChatGPT.com · Any MCP Client
Website · Getting Started · Documentation · User Guide
The Staging view: write what you want done. GiljoAI generates the mission and assigns agents from your templates.
Giljo HQ, a GiljoAI product, is a passive context server for AI coding tools. It stores your product knowledge, generates structured prompts, and coordinates multi-agent workflows via the Model Context Protocol (MCP). It does not write code or call any AI model. Your AI coding tool does all reasoning and coding using your own subscription.
GiljoAI sits at the intersection of product thinking and development. Whether you are a developer learning to define what you build before you build it, or a product manager turning a specification into working software, the platform gives you a structured path from vision to execution. The clearer your product definition, the more effective every agent session becomes.
Bring Your Own AI. GiljoAI works with Claude Code CLI, Claude.ai / Desktop, Codex CLI, ChatGPT.com, or any MCP-compatible tool. On Hosted, most tools connect with a one-click browser sign-in; terminal tools can also use an API key, which is what Community Edition's Connect tab gives you. You can run multiple tools simultaneously.
Windows (PowerShell):
irm giljo.ai/install.ps1 | iex
Linux / macOS:
curl -fsSL giljo.ai/install.sh | bash
The installer checks for prerequisites, downloads the latest release, sets up the database, builds the frontend, and walks you through configuration. When done, run python startup.py to start the server. First run opens the Setup Wizard in your browser.
Manual install (advanced)
git clone https://github.com/giljoai/giljo-hq.git
cd giljo-hq python install.py python startup.py
Requires Python 3.12+, PostgreSQL 18+, Node.js 22.23.3+.
Using VS Code? This repo ships a .vscode/mcp.json pointing at your local Giljo HQ install (http://localhost:7272/mcp) — open the folder and VS Code's MCP integration picks it up automatically. No copy-pasting a connect command.
GiljoAI never touches your AI credits. You bring your own Claude Code CLI, Claude.ai / Desktop, Codex CLI, ChatGPT.com, or any MCP-compatible tool, each with your own subscription. GiljoAI acts as a passive MCP server: your tool connects over HTTP, reads context and coordination data, and does all the reasoning and coding itself.
Create a Product to represent the software you are building. Fill in context fields: description, tech stack, architecture, testing strategy, and more. Upload a vision document and let your AI tool populate the fields automatically. Vision documents are the most impactful input you can give GiljoAI. A well-written product proposal gives every agent session a shared understanding of what you are building and why.
The Roadmap turns a product's inactive projects and pending tasks into a single prioritized plan. Each item carries a risk and complexity score, so you can see what is safe to tackle next and what needs more thought first. Drag to reorder. Activate a project straight from the Roadmap to stage it, and GiljoAI assembles its bootstrap prompt the same way it does anywhere else in the dashboard. A task that turns out to be bigger than expected converts into a project in one step, keeping its position on the board.
One skill is installed on your machine during setup. Use it from your CLI without breaking flow:
| Skill | Claude Code | Codex CLI | What it does |
|---|---|---|---|
| Projects and tasks | /giljo | $giljo | Capture tasks, create or update projects, and look them up mid-session — one command routes both create and read |
Agent templates need no installation at all. The Agent Template Manager in the dashboard lets you customize agent profiles with roles, expertise, and chain strategies, and every agent your orchestrator starts is handed its own profile — role, instructions, rules, success criteria — by the server the moment it begins work. An edit applies to the very next agent you launch. To run an agent yourself instead, choose Download profile (.md) from its row menu and drop the Markdown into any tool.
Each completed project writes to 360 Memory automatically: what was built, key decisions, patterns discovered, and what worked. This is not a plugin; it is a core product behavior. Your next project starts with accumulated context from previous ones. You control how many memories back agents read through the context settings. Optionally enrich memory with git commit history. Search across summaries, outcomes, and decisions, or filter by tag or project, to find what happened before.
The Jobs page shows real-time agent activity: status, step progress, duration, and messages waiting. A message composer lets you talk directly to the orchestrator or broadcast to the entire agent team. All messages are logged in the MCP message system for auditability.
The Message Hub is where agents coordinate across sessions and machines: persistent threads with participants, messages, and a baton that tracks whose turn it is. An agent on a different CLI tool or a different machine can join the same thread and pick up right where another left off. The dashboard view of a thread is an audit record for you to read. Nothing shown there is fetched back into an agent's context automatically.
This is the Giljo HQ Community Edition, free for single-user use under the Elastic License 2.0.
| Community Edition (Free) | SaaS Edition |
|---|---|
| Self-hosted on your machine | Managed hosting: nothing to install |
| Full context assembly and agent coordination | Everything in CE, plus: |
| 6 agent templates + customization | Sign in with Google or GitHub |
| Real-time dashboard and monitoring | Nightly encrypted backups you can download or restore |
| Unlimited projects, up to 16 active agent slots | Self-service Solo subscription and billing |
| No telemetry, no cloud dependency | Managed updates: always on the latest version |
| Layer | Technology |
|---|---|
| Backend | Python 3.12+, FastAPI, SQLAlchemy 2.1 (async), Alembic |
| Database | PostgreSQL 18 (required) |
| Frontend | Vue 3 (Composition API), Vuetify 4, Vite |
| Real-time | WebSocket via PostgresNotifyBroker |
| Auth | JWT httpOnly cookies, CSRF double-submit |
| Protocol | Model Context Protocol (MCP) over HTTP |
Production (single port):
Browser --> :7272 (FastAPI) --> API + WebSocket + MCP + Static files --> PostgreSQL (localhost:5432)
Development (two ports): Browser --> :7274 (Vite HMR) --> proxies /api, /ws, /mcp --> :7272 (FastAPI) --> PostgreSQL (localhost:5432)
Database always runs on localhost. Auth is required for all connections. Multi-tenant isolation is enforced at the database level on every query.
python install.py # Production install (recommended)
python install.py --dev # Developer install (adds pre-commit hooks, NLTK data) python install.py --headless # Non-interactive mode for CI/CD
python startup.py # Auto-detect mode and start
python startup.py --dev # Development mode with Vite hot-reload python startup.py --setup # Re-run the Setup Wizard python startup.py --no-browser # Start without opening the browser python startup.py --verbose # Detailed logging
| Mode | Ports | Use case |
|---|---|---|
| Production | Single port 7272 | Users running the product |
| Development | API 7272 + Frontend 7274 | Contributors making code changes |
| Document | Description |
|---|---|
| User Guide | Every page and feature, from code inspection |
| Product Overview | What it is, who it is for, the Six Pillars |
| Getting Started | Post-install walkthrough, from setup wizard to first project |
| Installation Guide | Complete installation reference |
| [MCP Tools Reference](docs/MCP_TOOLS_RE
앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요