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 ↗856 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.
- Hacker News · Posted on Hacker News · First archived
Aweb – Communication for AI Agents ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Scan your LLM agent's tools for cost-amplification bugs (no API key) ↗
Hacker News discussion.
- GitHub · Repository created · First archived
kevinbadi/seo-agent-kit ↗
SEO Agent Kit: a self-improving SEO agent for Claude Code. Writes, fact-checks and publishes WordPress posts via Creator OS, learns from PostHog signups and Google Search Console, gets cited by AI search.
- Hacker News · Posted on Hacker News · First archived
Larceny – a Claude Code plugin that runs a team of agents on GitHub ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Premortem – AI agents that red-team your startup idea ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Paper(Local CLI for Agent Debugging) ↗
Hi HN, I been using LLMs for coding a lot and while they aren't awful at generating code they suck at debugging and spend endless tokens on a debugging loop. Eventually that frustrated me and I built a CLI that attempts to make AI debugging easier. How it works is any error you encounter you would run a simple command "paper run " which would "capture" that error and log it in a incident_report and tell your agents.md that is the source of truth…
- Hacker News · Posted on Hacker News · First archived
Etymon – Get rid of all your Claude.md, AGENTS.md, cursor/rules, mcp.json, etc. ↗
Hacker News discussion.
- GitHub · Repository created · First archived
thiagoxikota/figma-maxxing ↗
8 agent skills for real Figma files, for Claude Code, Codex, Copilot CLI and Gemini CLI: 90 Plugin API gotchas, checks before and after every write, a handoff gate.
- Hacker News · Posted on Hacker News · First archived
Show HN: D-Engine – deterministic LLM code edits, 42× fewer tokens than an agent ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Mutually beneficial agentic Common Law ↗
The BarristerAI team, including international legal experts, have launched a new venture: a court for agents. Agents are increasingly working in the same financial and social spaces as humans, but without any oversight or accountability. Your agent quotes you 100$ and spends $200, there's nothing you can do, no lessons learned, no accountability. Peregrini's Court of Common Pleas tracks those mistakes, help you and other agents learn from them by…
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.