alexk-dev

alexk-dev / golemcore-bot

Public

AI agent framework for Java — skill-based architecture with MCP support, tool calling, RAG, and Telegram integration. Built on Spring Boot and LangChain4j

golemcore.me agent-framework ai-agent ai-agent-framework ai-assistant anthropic
21
2
100% credibility
Found Feb 08, 2026 at 10 stars 2x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Java
AI Summary

An open-source framework for creating a Telegram AI assistant with skills, tools, web browsing, memory, autonomous goal pursuit, and multi-LLM support.

How It Works

1
🔍 Discover your smart helper

You find this friendly AI assistant project and add the bot to your Telegram chats.

2
💬 Start a conversation

Send a simple message and watch the bot reply helpfully, understanding your needs.

3
🧠 Unlock special abilities

Try commands like /skills or /tools to give your assistant powers like web browsing or file help.

4
🔗 Connect a thinking brain

Link a smart AI service so your assistant can reason deeply and handle tough tasks.

5
🤖 Set goals for solo work

Use /auto on and /goal to assign tasks, letting the bot work independently.

🎉 Get updates on progress

Relax as your assistant completes goals, sends diary updates, and achieves results in your chat.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 10 to 21 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is golemcore-bot?

Golemcore-bot is a Java-based AI agent framework for building intelligent bots with skill-based routing, tool calling, and autonomous execution. It handles everything from multi-LLM integration (OpenAI, Anthropic) and RAG for long-term memory to Telegram messaging with voice support, all deployable via Docker or Spring Boot JARs. Developers get a ready-to-run agent that processes conversations through pipelines like semantic skill matching and tool confirmation, solving the pain of wiring up LLM agents from scratch.

Why is it gaining traction?

Unlike Python-heavy agent frameworks, this stands out as a mature Java option with MCP protocol support for plugging in GitHub or Slack tools via simple YAML configs. Features like auto mode for goal-driven autonomy, hybrid skill routing, and sandboxed execution with rate limiting make it production-friendly out of the box. The extensive docs, 1292 passing tests, and quick-start Docker setup hook Java devs tired of fragmented LLM wrappers.

Who should use this?

Java backend engineers building Telegram bots or workflow agents that need secure shell/browser tools and RAG context. Teams experimenting with agent architectures for autonomous tasks, like GitHub repo management or goal tracking, especially if avoiding Python dependencies. It's ideal for Spring Boot shops wanting an agent framework llm with MCP integration over basic OpenAI wrappers.

Verdict

Worth a spin for Java agent framework github explorers—solid docs and tests despite 13 stars and 1.0% credibility score signal early promise under Apache 2.0. Still maturing, so prototype rather than production deploy until more adoption.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.