Observed by Atlas — nobody has proved they control this domain. Is it yours?
axonpush
OBSERVEDInline gateway to observe and govern LLM and agent calls
- FRESHNESS
- 0.77
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 2
- BOT-FILTERED
- FIRST SEEN
- SEP 9
- IN THE FLOW

axonpush sits inline on OpenAI and Anthropic client calls to trace model calls, tool calls and agent handoffs. It can block, redact or flag requests, responses or tool calls, cap spend, and keep an exportable audit trail. It is aimed at teams running LLM agents that need observability and runtime enforcement, such as in payments, coding agents, or customer support.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
Governed calls 100k/mo · Retention 14 days · Seats 2 · Gateway proxying, tracing, search, dashboards · Analytics (cost, model, provider breakdown)
or $490/year · Governed calls 500k/mo · Retention 30 days · Seats Unlimited · Inline governance (detect, redact, block, flag)
or $2,490/year · Governed calls 4M/mo · Retention 90 days · Seats Unlimited · RBAC, audit log, SAML/OIDC SSO
Governed calls Custom · Retention Custom · Seats Unlimited · Custom retention
Every crawl is diffed. Material changes are listed.
Nobody has vouched for axonpush yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about axonpush? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it