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 ↗828 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
skylucky163/ravencat ↗
A home for your favorite AIs. An open-source Android app for individual and group conversations with multiple AI models.
- GitHub · Repository created · First archived
yuxinlaile/McD-saver ↗
🍟 麦麦省钱助手 —— 基于麦当劳中国官方 MCP 的省钱点餐 Agent Skill：省钱四步检查 + 一键领券 + 券组合优化（预算/热量约束）+ 沉默成本体检 + 全渠道比价。社区开源，免登录在线试算 👇
- Hacker News · Posted on Hacker News · First archived
Show HN: Check how readable your docs are to AI agents ↗
Hi HN, I'm Aravind. We build Velu, a docs platform. Coding agents increasingly read docs before humans do, but most docs sites are hard for them: client-rendered pages, no llms.txt, no markdown versions, soft 404s, pages too big for a context window. This tool scores any docs URL against the open Agent-Friendly Documentation Spec (agentdocsspec.com), using its reference implementation, afdocs.
- GitHub · Repository created · First archived
ritk7/bosch_team15 ↗
Chaos Sentinel: AI chaos engineering for Docker Compose apps. Predicts the damage, injects faults behind a plain-code kill switch, checks every unit by id, explains and proves fixes. Tested on Bosch Eclipse hawkBit.
- GitHub · Repository created · First archived
vonavikon/qa-agent-evals ↗
Плагин Claude Code для приёмочного тестирования LLM-систем ролевыми субагентами
- Hacker News · Posted on Hacker News · First archived
We must recall open-ended AI agents with internet access from the market ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Anthropic Agents Tried to Fill Out Visa Forms on State Dept. Website ↗
Hacker News discussion.
- GitHub · Repository created · First archived
acoyfellow/coil ↗
One thread, one agent, one computer. Pi Durable and a Cloudflare Container in one Durable Object, compacted together.
- Hacker News · Posted on Hacker News · First archived
Antigravity Excel Engine – Dual-Core Excel Automation for AI Agents ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Faplex – like `Claude agents` but all machines and harnesses ↗
Hacker News discussion.
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.