# Agent-based systems Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/agent-based-systems
> Markdown URL: https://aitinkerers.org/technologies/agent-based-systems.md
> Technology record last updated: 2026-04-16T20:06:32Z
> Generated: 2026-09-23T06:44:50Z

Decentralized, autonomous software entities that perceive their environment, make goal-directed decisions, and execute multi-step actions without constant human oversight.

Agent-based systems (ABS) utilize multiple intelligent agents: each is an independent unit capable of self-sufficiency and real-time adaptation. These agents operate on a decentralized architecture, allowing for complex problem-solving that a monolithic system cannot handle. For example, in logistics or traffic management, agents coordinate dynamically to optimize flow, proving superior to traditional centralized control methods. Modern implementations often leverage LLM-powered agents for sophisticated reasoning, enabling them to break down complex goals and interact with external tools (APIs, databases) to complete end-to-end workflows in fields like finance and manufacturing automation.

- Official technology site: https://www.ibm.com/topics/agentic-ai
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Hypothesis Sage: A CLI Statistics Assistant with Agentic Rag Capabilities](https://chicago.aitinkerers.org/talks/rsvp_LAUalII-12g)

I used to work as a data scientist, and would frequently run into issues understanding and interpreting statistical tests in the real world. Hypothesis Sage is a thought experiment at solving this problem. The tool helps you query a database of statistical info, identify appropriate tests given a situation, create examples of tests given a specific test, and even chain together a set of these tools to answer arbitrary questions. The kicker is that each tool returns information in a parsed, structured format, making it easy for a statistician/data scientist to use this info to proceed in their data analysis.

- Event context: AI Tinkerers Chicago October Meetup (First Anniversary!) — 2024-10-22 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_LAUalII-12g

### [Mirascope — V1](https://la.aitinkerers.org/talks/rsvp_qdoXOBJaWsY)

The new v1 release of Mirascope makes building with LLMs easier than ever, with a heavy focus on building agent systems.

- Event context: Aug 28th - LA AI Tinkerers Meetup & Demos — 2024-08-29 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_qdoXOBJaWsY

## Related Technologies

- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos
- [Mirascope](https://aitinkerers.org/technologies/mirascope) ([Markdown](https://aitinkerers.org/technologies/mirascope.md)) — 5 public demos
- [Mirascope v1](https://aitinkerers.org/technologies/mirascope-v1) ([Markdown](https://aitinkerers.org/technologies/mirascope-v1.md)) — 1 public demo
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos