# Agents & LLMs Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/agents-llms
> Markdown URL: https://aitinkerers.org/technologies/agents-llms.md
> Technology record last updated: 2026-03-13T08:10:47Z
> Generated: 2026-09-21T13:42:34Z

Agents & LLMs are autonomous systems: They combine a Large Language Model (LLM) with planning, memory, and external tools to execute complex, multi-step tasks without continuous human oversight.

This technology moves LLMs beyond simple chat responses: Agents integrate the LLM (the 'brain') with a core loop of reasoning, action, and observation. Key components include a memory module (for context and history), a planning module (for task decomposition), and a toolset (for external actions like web search or code execution). Projects like AutoGPT and BabyAGI first demonstrated this autonomy; today, enterprise frameworks like LangChain, CrewAI, and Microsoft's Autogen standardize development. The objective is clear: Delegate complex, sequential workflows, allowing the system to self-correct and achieve high-level goals—for example, a financial agent analyzing Q2 earnings calls and summarizing key technological moats.

- Official technology site: https://developer.nvidia.com/blog/introduction-to-llm-agents/
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Context Engineering](https://dallas-fort-worth.aitinkerers.org/talks/rsvp_9550Ss4Fa18)

ReKnew pioneered Context Engineering to bring Dara to knowledge to Enterprise AI to unlock agentic and generative AI use cases.

- Event context: AI Tinkerers – Dallas-Fort Worth Inaugural Meetup · 31 July 2025 — 2025-07-31 — Dallas Fort Worth
- Public talk page: https://dallas-fort-worth.aitinkerers.org/talks/rsvp_9550Ss4Fa18

### [Automating What 400 People Do: Building an AI Agent for Trade Compliance](https://medellin.aitinkerers.org/talks/rsvp_PmGOZyw0ohk)

We’re building an AI system to automate what 400 people currently do manually in a major customs agency: extracting fragmented information from import documents, interpreting it with legal logic, and delivering structured data that complies with government regulations (in our case, the Colombian DIAN). This is not just extraction — it’s the orchestration of multiple AI agents to read, interpret, and decide. We’ll demo a working prototype that receives documents and provide all the import process to your goods.

- Event context: AI Tinkerers Medellín #11 - Science Fair - Agentes en acción — 2025-04-01 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_PmGOZyw0ohk

## Related Technologies

- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 215 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Demo Deck](https://aitinkerers.org/technologies/demo-deck) ([Markdown](https://aitinkerers.org/technologies/demo-deck.md)) — 1 public demo
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos
- [OCR](https://aitinkerers.org/technologies/ocr) ([Markdown](https://aitinkerers.org/technologies/ocr.md)) — 10 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [Reknew](https://aitinkerers.org/technologies/reknew) ([Markdown](https://aitinkerers.org/technologies/reknew.md)) — 1 public demo
- [Vercel](https://aitinkerers.org/technologies/vercel) ([Markdown](https://aitinkerers.org/technologies/vercel.md)) — 48 public demos