Stop blind agent fan-out before it taxes the machine.
Axon is a local MCP server that helps agents understand when the machine is the bottleneck, before they spawn more tools, burn more credits, or debug the wrong problem.
Engineering analysis, not marketing claims.
A public research log for real scenarios: same task with and without Axon, measured locally, with the tradeoffs shown instead of hidden.
With and without Axon: app build, test, helper fan-out, and output preservation.
The same app task was run in independent workspaces. Axon avoided extra tool helpers, reduced concurrency, preserved output, and made the tradeoff explicit.
Turning local runtime pressure into value metrics users can understand.
Risky tool spawns avoided, estimated credits saved, developer time protected, and stale local runtime count.
Why agentic workflows need host awareness before they run more tools.
OOMs, stuck sessions, large local logs, slow builds, and false debugging paths all point to a missing runtime signal.
A generic demo for agent IDEs, app builders, local runners, and GPU boxes.
How Axon sits beside any agent runtime and returns run, degrade, defer, cleanup, and safe_parallelism decisions.
The bottleneck moved below the prompt.
Modern coding agents can plan, edit, test, spawn tools, drive browsers, and call MCP servers. But they usually do it blind to the local machine they are running on.
Tool servers accumulate
Old MCP servers, stale shells, renderers, and browser controllers quietly compete with every new agent task.
Agents blame the code
When hardware pressure causes flaky tests or slow builds, the agent may debug false software problems instead of reducing local pressure.
Users feel the slowdown
The visible outcome is lag, OOMs, fan noise, slow IDEs, failed browser automation, and wasted tokens.
What Axon gives an agent
Example decision
$ axon query workload_advice
{
"recommendation": "defer",
"risk": "critical",
"safe_parallelism": 1,
"reasons": [
"Disk at 96% (Critical)",
"System impact is critical",
"Current anomaly is memory_pressure"
],
"suggested_actions": [
"defer new heavy work",
"cap parallelism at 1 instead of 4"
]
}Built for the agent infrastructure layer.
Axon is useful anywhere agents run on machines: laptops, workstations, developer VMs, CI-like local runners, GPU boxes, and hardware platforms.
Agent IDEs and app builders
Prevent runaway local fan-out, surface host constraints, and make “why is my agent slow?” answerable without cloud telemetry.
NVIDIA, AMD, Apple, workstation OEMs
Expose local capacity and bottlenecks as a standard primitive agents can use before GPU, compile, and browser workloads.
Faster feedback with fewer false failures
Keep useful work moving while avoiding memory storms, thermal throttling, stale MCP servers, and broken long sessions.
Install once. Every local agent gets hardware context.
Axon is private by architecture: no telemetry, no analytics, no cloud calls. It speaks MCP over stdio and runs locally.
# Homebrew
brew install rudraptpsingh/tap/axon
# Configure agents
axon setup
axon setup cursor
axon setup vscode
# Try it directly
axon query agent_runtime_health
axon query workload_adviceMake local runtime a first-class agent signal.
Axon turns host pressure into execution policy, so agents can prove value with fewer failed runs, fewer unnecessary tool workers, and clearer user-facing impact.