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 ↗857 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
Minglink/hark-agent-mobile ↗
Hark Agent Mobile — 拥有自定义系统提示词注入的独立 Linux 终端运行环境与任务规划引擎的手机端自主 AI 智能体，求个星星收藏
- GitHub · Repository created · First archived
Simreal-AI/Simreal-MLBench ↗
[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.
- GitHub · Repository created · First archived
lobehub/acceptance ↗
✅ Acceptance is open-source e2e testing for Agents. Your coding agent turns a prompt into observable checks, runs the real product, and publishes a report with screenshots, recordings, and logs attached to each check. You can accept the work, or send individual checks back.
- GitHub · Repository created · First archived
xsoway/codebase-graph-prd-rules ↗
Two source-verified AI-agent skills that turn project code into traceable business-rule documents (whole-project + single-module). Graph-guided, evidence-graded, evaluation-backed.
- GitHub · Repository created · First archived
axiom-desu/ZCodium ↗
Modified ZCode.
- GitHub · Repository created · First archived
ChenneyZhuang/laya-browser-agent ↗
Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwright/CDP, MCP-friendly.
- GitHub · Repository created · First archived
OneMoh/html-explainer ↗
把一个主题做成有配音、字幕、封面的讲解分析类视频 —— 全本地、用 HTML 写画面，稳定音画同步。 面向 AI 编程智能体的确定性 HTML → MP4 渲染流水线。
- GitHub · Repository created · First archived
HeyPuter/builder ↗
📦✨ AI Builder For Creating Sites and Apps! An open-source alternative to Lovable, Replit, v0, and similar platforms.
- GitHub · Repository created · First archived
ZephyrDeng/ego-jev ↗
ego lite skill — each DOM step decided in ~0.4s, no LLM turn
- GitHub · Repository created · First archived
freestylefly/WeChatBridge ↗
微信聊天记录一键转发到 AI Agent 与 Obsidian 的原生 macOS 工具
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.