THE INTERNET IS THINKING
Earlier sources: AI agents
AI agents use models to choose actions, call tools, and work toward a goal. This thread follows agent frameworks, memory, orchestration, evaluation, and safeguards; autonomy and reliability vary between systems.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗814 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- GitHub · Repository created · First archived
uncovertechtalent/cto-powersuit ↗
The CTO powersuit is a set of agent skills, one module per CTO function from the deploy gate to the hand-over, that one person uses to run a company's whole engineering platform.
- GitHub · Repository created · First archived
yoanbernabeu/skillcrew ↗
One skill registry for your whole team, in every AI coding agent, always up to date.
- GitHub · Repository created · First archived
sepehr071/awesome-iran-mcp ↗
19 open-source MCP servers (308 tools) that give AI agents the Iranian web: Digikala, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche and more. Prices in Toman.
- GitHub · Repository created · First archived
MalganisWu/red-bean-nian-gao ↗
AI Agent 对话平台 —— 流式对话、工具调用、子 Agent 委派、定时任务，以及每一次运行的完整审计轨迹。
- GitHub · Repository created · First archived
MalganisWu/red-bean-qing-tuan ↗
可嵌入的 TypeScript Agent Runtime —— model→tool 循环、checkpoint、interrupt 屏障，零生产依赖，可嵌进任何宿主。
- GitHub · Repository created · First archived
skrrt-sh/motty-sdk ↗
The toolkit for building motties, models made of code, not weights. LLMs are layer 1. A motty is layer 2, below your agents, and to them it is one more model. Inside, it is your TypeScript. It fits the stack you have, as your gateway or beside it.
- GitHub · Repository created · First archived
chen-xinyi111/ecommerce-ai-after-sales ↗
电商智能售后服务台：订单查询、AI 咨询、售后申请、人工协作与客服审批办理。Vue 3 / FastAPI / LangGraph。
- Hacker News · Posted on Hacker News · First archived
I build an open-source runtime security layer for AI agents – Let's break it ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: An Agentic Virtual Machine ↗
I'm interested in feedback pertaining to the features in my agentic harness project. * Addressable Memory Everything in the context is divided into receipts with internal urls that the model can address, with a "pulled preview" approach where dozens of spammy tools can be streaming output at the same time without flooding the attention window. * Perpetual Context Plurnk has no compaction algorithm because the addressable memory empowers the model…
- GitHub · Repository created · First archived
Adicodes270/Study-AI-Agent ↗
Making An AI agent to automate studying stuff for me
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI agents
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.