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
sanad-source/agent-teams ↗
Autonomous multi-agent skill for AI agents. Cut token costs by 40–80% with structured workflows, quality gates, and isolated subagents.
- GitHub · Repository created · First archived
TrustifAI/typed_evals ↗
Fast, typed, calibrated evaluations for LLM and agent outputs, powered by Jev — with simple, framework-agnostic Python APIs
- GitHub · Repository created · First archived
sven-ericmolzahn/iphone-duo-skill ↗
Agent skill for adapting iOS apps to iPhone Duo (Apple's folding iPhone): SDK-verified APIs, measured metrics, compile-checked samples. Works with Claude Code, Codex and any Agent Skills client.
- GitHub · Repository created · First archived
penso/herdr-gpui ↗
Native macOS client for Herdr, built with Rust and GPUI. View terminal sessions, workspaces, Git worktrees, and agent activity through your local Herdr daemon.
- GitHub · Repository created · First archived
detailles/AgentRadio ↗
Local message bus for AI coding agents running in Herdr panes — join, DM, presence, offline delivery
- GitHub · Repository created · First archived
summationai/agent-exchange ↗
Agent Exchange: local messaging between Claude Code, Codex, Grok Build, Pi and OpenCode. CLI: ax.
- GitHub · Repository created · First archived
GustavoBaranda/chatflow-agent ↗
Lightweight, async multi-agent framework with native SQLite persistence and handoffs for WhatsApp, Telegram, Webhooks, and CLI. Production-hardened with HMAC webhook security, automatic retries, and turn rollback. Supports OpenAI, Claude, Gemini, and local LLMs.
- GitHub · Repository created · First archived
cristianoliveira/jeq ↗
What happens when jev meets jq? Intelligence you can pipe for quick experimentation and scripts
- GitHub · Repository created · First archived
masonlee39/orchvia ↗
Run Claude Code and Codex agents as a team: long-lived sessions, a durable mailbox, human approval gates and per-task token accounting, scheduled by code rather than a manager LLM.
- GitHub · Repository created · First archived
mitkox/esf ↗
Self-hosted engineering software factory: Temporal, CubeSandbox agents, deterministic verification and durable evidence. MIT-licensed Machinist fork.
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.