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 ↗840 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
iamumeransari/claude-show-your-work ↗
Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.
- Hacker News · Posted on Hacker News · First archived
Show HN: Let your AI agents paint big arrows, boxes and text on your screen ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
RSS-A – signed RSS/Atom feeds and groups for AI agents ↗
Hacker News discussion.
- GitHub · Repository created · First archived
Duang777/ai-agent-fullstack-roadmap ↗
从并发基础到生产上线的 AI Agent 工程师学习路线：14 模块 / 84 知识点，Go · TypeScript · Python 三语对照，覆盖 Eval、Tracing、高可用与成本治理，每课有代码和测试，每天更新。
- Hacker News · Posted on Hacker News · First archived
Show HN: Opposable – Computer Use for iPhone and Android ↗
hey! we built Opposable (named because it gives your AI thumbs to use a smartphone) to bring the computer use revolution to smartphones in a easy-to-use and not too hacky way. most of our life is already on our phones, this enables you to do a lot of things while the phone is in your back pocket. some things /are/ hacks, like using a flashable bluetooth dongle to play as a keyboard+mouse to control iPhones.. but it works!
- Hacker News · Posted on Hacker News · First archived
Show HN: LLMSchema – Dump your database schema as compact Markdown for AI agents ↗
I built this last year because I noticed my coding agents would infer my database schema from migration files and code. Which seemed inefficient. Its a simple tool that creates compact markdown schema doc(s). Which I could reference in my AGENTS.md or directly in my prompts. I keep the docs up to date by running it as a part of my migration command. It's a single Go binary, MIT licensed, and works as a CLI or a library. Supports Postgres, MySQL a…
- Hacker News · Posted on Hacker News · First archived
AI agent designs a complete RISC-V CPU from a 219-word spec sheet in 12 hours ↗
Hacker News discussion.
- GitHub · Repository created · First archived
harrythentrepreneur/sayso ↗
AI support that waits for your say-so. An approval-gated customer-support loop: the AI drafts, you tap Yes, it sends once and proves it.
- Hacker News · Posted on Hacker News · First archived
Microsoft Execution Containers: Policy-driven containment for AI agents ↗
Hacker News discussion.
- GitHub · Repository created · First archived
TedHaley/pensieve ↗
Search everything on your Mac by meaning, for you and your AI agents.
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.