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 ↗811 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
onehumanbeing/esp32-iphone-agent ↗
Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.
- GitHub · Repository created · First archived
GlacierHubAB/den ↗
See, approve and steer all your Claude Code agents from one terminal screen.
- GitHub · Repository created · First archived
electricsheephq/heartbeat2 ↗
HeartBeat 2.0 — wakes and watchers for Hermes Agent: your agent follows up in the same chat, on the same model, and stays quiet when nothing changed.
- GitHub · Repository created · First archived
molang163/chinese-natural-reply ↗
这个skill旨在让GPT说话像人，改善防御性回复，不套安慰模板，说大白话。与同类skill对比，说人话的能力排名第一（Codex skill，附盲评对比）
- GitHub · Repository created · First archived
arbazsiddiqui/voxlock ↗
The best performing voice isolator there is. Keeps the caller's voice and removes the other voices in the room before speech-to-text hears them. Open source, streaming, runs on CPU and in the browser. pip install voxlock
- GitHub · Repository created · First archived
ybak/agentscope-2.0-tutorial ↗
一本开源的 AgentScope Java 中文教程：7 篇 44 章、839 页成书体量的完整 Markdown 源稿，由浅入深覆盖从第一个 Agent 到生产级 Agent 平台的全部主题。
- GitHub · Repository created · First archived
zero-lab-ai/skills ↗
Portable, evidence-bound security skills for authorized defensive assessment, red teaming, penetration testing, detection engineering, and engagement operations.
- Hacker News · Posted on Hacker News · First archived
AI Agents create their own backstories for a Love is Blind simulation ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Artex AI, Claude agents used in cyberattacks on South Korean banks ↗
Hacker News discussion.
- GitHub · Repository created · First archived
aadityakumarsah/trycanari ↗
Bug bounties for AI agents: canary-verified attacks, paid in shielded ZEC
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.