Collect public sources
Read official pages, GitHub releases, feeds, packages, and papers. Collection does not require paid search.
Agent Radar · Scheduled Markdown research
Agent news, with sources
Collect public agent news on GitHub Actions and save sourced Markdown briefs and watchlists. Relevance and citation checks run before each commit.
$ python scripts/agent_radar.py brief
CORE FILES
-
radar.md -
agent-watchlist.md -
user-field-notes.md -
playbook.md -
storage-angle.md
radar.md Thesis: local agents win on evidence · Changed: sandbox snapshot noise · Open: who owns artifact storage
Markdown-first · GitHub Actionschecks before commit · Git as audit
One research loop
Research you can review in Git
Markdown files hold the research. A lightweight model screens sources and another drafts the report; the runner checks proposed changes before committing them.
Illustrative sample radar.md · sample week
Current thesis Local agents win on evidence
Coding agents that keep workspace artifacts local are easier to audit than chat-only hosted flows.
Changed Sandbox + snapshot noise
More products advertise sandboxes; few document snapshot retention or replay cost.
Open questions Who owns the artifact store?
When agents write logs, checkpoints, and playbooks, which storage path is intentional vs incidental?
Auditable state
What the pipeline leaves in Git
The runner updates weekly theses, the agent watchlist, field notes, and storage implications within fixed write bounds. When a candidate enters the watchlist or brief, the change remains reviewable in repository history.
- 01
Weekly thesis
Current judgment, what changed, and open questions for the Agent industry.
- 02
Watchlist
Mainstream and emerging agents with evidence labels — not a raw link dump.
- 03
Field notes
Real workflows and reusable patterns captured as they show up in the wild.
- 04
Storage implications
Where agents keep workspace state, sandboxes, logs, and replay — a side lens, not the whole product.
From sources to a commit
From sources to a commit
Select and draft
Score relevance and remove duplicates before model screening and drafting. The model can update only designated research files.
Check before committing
Check citations, quota, language coverage, and freshness. Failed checks remain visible in telemetry and issues. Git records accepted changes.
Actions runs the loop
Actions runs the loop
Run on a schedule
Daily, weekly, and monthly jobs run on GitHub Actions and produce bilingual reports. Local runs are available for debugging.
Actions and cost
Actions and cost
No paid search required
Collection uses free public source lanes. Bring your own model keys: a lighter model can screen, a stronger one can draft, so spend stays intentional.