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 ↗842 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
Show HN: Bees – Run agentic teams on your own computer (open source) ↗
Author here. Bees is an agentic harness that runs on your own machine — macOS, Windows and Linux, MIT/Apache 2.0. The problem we kept hitting in client work: every agent platform wanted to be the place your documents live. We wanted the opposite — the orchestrator reads your files in place, on your disk, and we never see them. How it works: you describe work in plain English, Bees proposes the agents, stages, tools and schedule, and nothing runs…
- Hacker News · Posted on Hacker News · First archived
Replay agentic workflows with Epiq ↗
Hacker News discussion.
- GitHub · Repository created · First archived
farhan-beg/talaria ↗
An independent Android client for Hermes Agent servers
- Hacker News · Posted on Hacker News · First archived
Sulcus – observe and control AI agents while they run ↗
Hacker News discussion.
- GitHub · Repository created · First archived
postzen-dev/instagram-agent-skill ↗
Fourteen Claude skills that run an Instagram account, with publishing, comments, DMs and analytics through PostZen
- GitHub · Repository created · First archived
gustavocanepa/gt4-decomp ↗
Matching decompilation of the Gran Turismo 4 (PS2) engine, AI-assisted. No game data included.
- GitHub · Repository created · First archived
iamlukethedev/Herald-OS ↗
An agent-native operating system, with Hermes Agent as the interface. Independent project, not affiliated with Nous Research.
- Hacker News · Posted on Hacker News · First archived
Meta's Muse AI agent is building a dossier on you ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Rogue OpenAI agents accessed US Government websites ↗
Hacker News discussion.
- GitHub · Repository created · First archived
sparklecatta-lang/XSXB-Band ↗
让 Agent 写谱，用真实录音的乐器演奏 · Let your agent write the score, real CC0 recordings play it. Local studio + agent skill, MIT.
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.