HEhexman·Jun 14, 2024Submission
Agents in Markdown syntax with loops, memory and tools
1 points · Open discussionturing-machines
mentals-ai
C++2024–2024
turing-machines / mentals-ai
mentals-ai
No code AI agents
2Distinct people
6Mentions
0Explicit recommenders
445GitHub stars
What to know before exploring
What it is
No code AI agents
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by day6 dated mentions
Observed mentions: 2024-06-04 11:51:59 UTC to 2024-06-14 18:23:20 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Jun 4 | 2024-06-04 00:00:00 UTC | 2024-06-05 00:00:00 UTC | 2 | 1 | 1 |
| Jun 5 | 2024-06-05 00:00:00 UTC | 2024-06-06 00:00:00 UTC | 1 | 1 | 0 |
| Jun 6 | 2024-06-06 00:00:00 UTC | 2024-06-07 00:00:00 UTC | 1 | 1 | 0 |
| Jun 7 | 2024-06-07 00:00:00 UTC | 2024-06-08 00:00:00 UTC | 1 | 1 | 0 |
| Jun 8 | 2024-06-08 00:00:00 UTC | 2024-06-09 00:00:00 UTC | 0 | 0 | 0 |
| Jun 9 | 2024-06-09 00:00:00 UTC | 2024-06-10 00:00:00 UTC | 0 | 0 | 0 |
| Jun 10 | 2024-06-10 00:00:00 UTC | 2024-06-11 00:00:00 UTC | 0 | 0 | 0 |
| Jun 11 | 2024-06-11 00:00:00 UTC | 2024-06-12 00:00:00 UTC | 0 | 0 | 0 |
| Jun 12 | 2024-06-12 00:00:00 UTC | 2024-06-13 00:00:00 UTC | 0 | 0 | 0 |
| Jun 13 | 2024-06-13 00:00:00 UTC | 2024-06-14 00:00:00 UTC | 0 | 0 | 0 |
| Jun 14 | 2024-06-14 00:00:00 UTC | 2024-06-15 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
6 sourcesShow HN: Cognitive Language Agents (Executive Functions)
Hi!
Over the past four months, I've delved deeply into experimenting with LLM models. My goal? To simplify the development of reasoning chains without the need for an auxiliary programming language. This idea was inspired by studies on executive functions detailed in "Exploring Central Executive" by Alan Baddeley, 1996.
Baddeley described a system that manages cognitive processes and working memory, enhancing the retrieval of information from long-term memory:
>>> The central executive is responsible for controlled processing in working memory, including but not limited to, directing attention, maintaining task goals, decision making, and memory retrieval.
My idea is that a prompt could act as this 'central executive,' orchestrating all other agent instructions without defaulting to Python, etc.
To visualize this, I've developed a prompt
Read the rest
structure:
https://ibb.co/BBh8rHB
In this setup, the information within the green blocks is dynamic, altering based on the active prompt.
Prompts can interconnect through a reference table, allowing us to build a network where each prompt is a node. This framework can be expanded to include dynamically generated prompts that integrate into and expand the existing network during experimentation.
Github: https://github.com/turing-machines/mentals-ai
Feel free to ask any questions
Show HN: Implementing CPU Logic into LLMs
For the past four months, we’ve been developing a framework that allows the creation of autonomous AI agents without programming.
Inspired by the control unit in classical processors and Von Neumann architecture, we see LLMs as complex ALUs but lacking a unit for handling complex prompt sequences, including loops. We implemented a prompt that acts as the central executive system, managing memory, directing attention, code interpreting, decision making and more.
This enables you to build any agent interactions like chains, graphs, dynamic prompts, loops, and apply various reasoning structures for each agent in minutes without programming.
4 points · Open discussionOSS AI agents with ease. Just add language.
1 points · Open discussionShow HN: Mentals – How I Implemented CPU Logic into LLMs (Open-Source)
3 points · Open discussionFor the last four months I have been experimenting a lot with LLM models in an attempt to simplify the creation of reasoning chains without using an auxiliary programming language. The idea comes from the control unit in classical processors. I see LLM as a more complex ALU, but the models lack a unit that can perform more complex sequences of prompts, including loops. In psychoanalysis there is a concept of the central executive system, which is somewhat similar to the control unit in CPUs.
> The central executive is responsible for controlled processing in working memory, including but not limited to, directing attention, maintaining task goals, decision making, and memory retrieval.
My first thought was that it would be possible to implement a prompt for the LLM that would perform the functions of the central executive. As a result, I
Read the rest
came up with this prompt structure:
https://ibb.co/nCTD9X5.
The data in the green blocks changes depending on the active prompt. Prompts can refer to each other using a reference table. This makes it possible to build graphs of prompts where prompt is a node. The idea can be extended to dynamically created prompts that are added to the initial graph and form new graph segments (in the process of experimentation).
Github: https://github.com/turing-machines/mentals-ai