# Agentforge

> AI agent spec generator powered by Xiaomi MiMo V2.5 — describe an agent in plain language, get production-ready system prompt + tool definitions + test cases. Multi-format export (Cursor, Hermes, MCP, ChatGPT, OpenAI, Anthropic).

- **Type:** MCP server
- **Install:** `agentstack add mcp-khimsaja-agentforge`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Khimsaja](https://agentstack.voostack.com/s/khimsaja)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Khimsaja](https://github.com/Khimsaja)
- **Source:** https://github.com/Khimsaja/agentforge
- **Website:** https://agentforge-five-gamma.vercel.app

## Install

```sh
agentstack add mcp-khimsaja-agentforge
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# AgentForge

> **Bikin AI agent production-ready dalam 60 detik.**
> Input deskripsi → output system prompt + tool definitions + test cases. Export ke Cursor, Hermes Agent, MCP, ChatGPT GPT, OpenAI Functions, Anthropic Tools.

[](https://agentforge.kleinnn.my.id) [](LICENSE) [](https://aistudio.xiaomimimo.com)

---

## Why

The hardest part of building agents isn't the framework — it's the **spec**. A shallow system prompt loses to a well-structured one by 40-60% on real benchmarks. Most builders skip this step because writing rigorous prompts + tool schemas takes hours.

**AgentForge does it in 60 seconds.** Powered by Xiaomi MiMo V2.5 (reasoning + structured-output flagship), it converts a 1-3 sentence description into:

- ✅ **System prompt** — production-ready (400-1500 words), role + behavior + constraints + output format + edge case handling + anti-hallucination clauses
- ✅ **Tool definitions** — OpenAI/Anthropic/MCP-compatible JSON Schema, only the tools that make sense for the agent
- ✅ **Test cases** — 4-8 input/expected-behavior pairs covering happy path + edge cases + adversarial inputs
- ✅ **Multi-format export** — Cursor Rules, Hermes Skill, MCP Server boilerplate (TypeScript), Claude Code prompt, ChatGPT custom GPT, OpenAI Functions JSON, Anthropic Tools JSON

## Live demo

👉 **[agentforge.kleinnn.my.id](https://agentforge.kleinnn.my.id)**

Try the presets (Customer Service Bot, Code Reviewer, Trading Sniffer, Hermes Skill Maker, ...) or describe your own agent in plain Indonesian/English.

## Stack

- **Frontend**: Next.js 14 (App Router) + Tailwind CSS + TypeScript
- **Reasoning model**: Xiaomi MiMo V2.5 Pro (configurable via env)
- **API**: OpenAI-compatible streaming chat completions
- **Deploy**: Vercel Edge Runtime (60s max duration)
- **Storage**: localStorage (no DB, no auth, fully client-side state)

## Quickstart (local dev)

Requires Node.js 18+.

```bash
git clone https://github.com/agentforge-dev/agentforge.git
cd agentforge
npm install

# Configure model provider (any OpenAI-compatible endpoint works)
cat > .env.local 
  - suggestion: 
  - confidence: 0.0-1.0

Security focus: SQL injection (parameterized queries), XSS (escaping/sanitization),
SSRF, path traversal, hardcoded secrets, unsafe deserialization, ...

## Tools

- `read_file(path: string)` — fetch file content for context
- `run_static_analysis(path: string, lang: 'py'|'ts')` — invoke ruff/eslint
- `git_blame(path: string, line: number)` — see who introduced the line

## Test cases

1. Input: `` → flag as critical SQL injection
2. Input: `` → empty findings array
3. Input: `` → flag as high security
...
```

## AI tools used to build AgentForge

This project itself was built using AI agent tooling — the same workflow AgentForge optimizes:

- **Hermes Agent** — workflow orchestration (skills, terminal, file ops)
- **Claude Code (Sonnet 4.7)** — TypeScript / React authoring
- **9router** — local OpenAI-compatible LLM proxy for dev
- **MiMo V2.5** — runtime spec generation (will become primary post-grant)
- **Cursor** — fine-grained code edits
- **Vercel** — preview deployments
- **Tailwind CSS** + **shadcn/ui** patterns — UI

## Roadmap

- [x] Multi-format export
- [x] Streaming generation UX
- [x] Live demo on Vercel
- [ ] Spec versioning + diff viewer (git-style)
- [ ] Auto-evaluator: run `testCases` against spec on N models, score
- [ ] Multi-agent compositions (orchestrator + workers as a graph)
- [ ] 1-click deploy: spec → Cloudflare Worker / Vercel function
- [ ] Skill marketplace: share + remix specs (community CC0/MIT)

## License

MIT — see [LICENSE](LICENSE)

---

Built with ❤️ by [Klein](https://kleinnn.my.id) · powered by [Xiaomi MiMo V2.5](https://aistudio.xiaomimimo.com)

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Khimsaja](https://github.com/Khimsaja)
- **Source:** [Khimsaja/agentforge](https://github.com/Khimsaja/agentforge)
- **License:** MIT
- **Homepage:** https://agentforge-five-gamma.vercel.app

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-khimsaja-agentforge
- Seller: https://agentstack.voostack.com/s/khimsaja
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.