Design agents by chatting — describe what you need and they're live. They research, analyze, and deliver reports to your inbox, Slack, Telegram, Discord, or WhatsApp — without you asking. They learn from every run and get smarter over time.
We don't just say the agents work — we prove it with an automated eval suite scored by an independent LLM judge on every commit. Here's the current baseline, run against Claude Sonnet 4.6 with Opus 4.6 grading.
| Role | Passing |
|---|---|
| 🔎 Knowledge Agent | 4 / 4 |
| ⚙️ Backend Engineer | 5 / 5 |
| 🎨 Frontend Engineer | 4 / 4 |
| 🚀 DevOps Engineer | 5 / 5 |
| 🔍 QA Engineer | 4 / 4 |
| ✏️ UI/UX Designer | 4 / 4 |
| 📊 Data Analyst | 4 / 4 |
| 📈 Growth Analyst | 4 / 4 |
| 📢 Marketing Manager | 4 / 4 |
| 💼 Sales Rep | 4 / 4 |
| 💬 Customer Support | 4 / 4 |
| 📝 Technical Writer | 4 / 4 |
| 📋 Project Manager | 4 / 4 |
| 🎯 Recruiter | 4 / 4 |
| ⚖️ Legal Analyst | 4 / 4 |
| 💰 Finance / Bookkeeper | 4 / 4 |
Chatbots wait for you to ask. Our agents work autonomously — researching, analyzing, and delivering on a schedule. They learn from every run and get better at your business over time.
Just describe what you need. "I need a sales analyst that sends competitor intel every Monday." The system builds everything — instructions, schedule, integrations, delivery. No forms, no config files.
Agents work on a schedule — daily briefs, weekly reports, hourly health checks. Delivered to email, Slack, or Telegram. You wake up to intelligence, not a to-do list.
Every run teaches the agent what works. After a month, your competitor watch knows which search queries find real intel and which are dead ends. Switching cost compounds.
MongoDB, SSH, REST APIs — plus a wildcard connector for any service. Say "connect to Stripe" in chat, paste your key, and the agent can query your revenue in the next sentence.
Eight providers: Claude, GPT, Llama, Gemma, DeepSeek, Gemini, Ollama, or any OpenAI-compatible endpoint. Assign different models for different jobs — cheap for reports, smart for analysis.
After a few interactions the agent learns your preferences — tables vs paragraphs, brief vs detailed, which topics you care about. Every response gets more personalized without you asking.
Your sales analyst finds 5 qualified leads overnight. Your DevOps engineer checks your servers every 4 hours. Your content strategist has next month's calendar ready on the 1st. All delivered to your inbox before your coffee is ready. No chatting required.
Here's everything the team's knowledge base currently contains on both topics:
customer:acmebilling,decisionEach one is a focused agent with its own system prompt, tool selection, and regression suite. Toggle any of them on or off from the admin page.
Paste a credential, click Test connection, it's live. No code changes, no restarts. Everything encrypted at rest with Fernet, every change logged to the audit trail.
git clone to "signed in."
One repo. One env file. One docker compose up.
Smart Agents Pro brings its own Mongo, its own JWT secret, and the app
container. You bring an LLM key.
# 1. Clone the repo $ git clone https://github.com/choochtech/smart-agents-pro.git $ cd smart-agents-pro # 2. Configure — set at least ANTHROPIC_API_KEY in .env $ cp .env.example .env $ nano .env # or your editor of choice # 3. Bring the stack up (app + mongo sidecar) $ docker compose up -d # 4. Open the app — first signup becomes the admin $ open http://localhost:8090
Set one of: ANTHROPIC_API_KEY, OPEN_AI_API_KEY, GROQ_API_KEY, CEREBRAS_API_KEY, GEMINI_API_KEY, OPENROUTER_API_KEY. Or point at a local Ollama.
Set AI_AGENTS_ADMIN_EMAIL + AI_AGENTS_ADMIN_PASSWORD in .env before booting, or let the first visitor sign up as admin.
From the Integrations admin page, paste credentials for GitHub, Jira, Slack, databases, etc. Click Test connection, it's live.