Status basis: npm_downloads_7d gained 32 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 32 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 27 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 27 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -5 per 3d from 32 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 27 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -5 per 3d from 32 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 27 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | inferred | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | 1 | inferred | 1 quote(s) |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | mcp | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
It addresses the critical pain point of invisible AI agent behavior by providing real-time call tracking, making it essential infrastructure for trustworthy AI workflows.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“Screening needs `TYPESAFE_API_KEY`”— readme
“npm install -g agent-chaperone”— readme
“screening sends the arguments and results being screened to the configured model backend”— readme
“A calibrated firewall for AI agent tool calls.”— readme
“agent-chaperone screens an AI agent's tool calls before they run”— readme
FAQ
What is Agent Chaperone?
A tool for developers and technical teams to visualize and audit real-time AI agent API calls and outputs, ensuring transparency and traceability in agent behavior.
What does Agent Chaperone do?
Monitor AI agent API calls and output results during task execution to verify expected behavior and maintain auditability.
Why does Agent Chaperone matter?
It addresses the critical pain point of invisible AI agent behavior by providing real-time call tracking, making it essential infrastructure for trustworthy AI workflows.
Is Agent Chaperone open source?
Yes — Agent Chaperone is open source.
Can I self-host Agent Chaperone?
Yes — Agent Chaperone can be self-hosted.
What does Agent Chaperone integrate with?
mcp
How popular is Agent Chaperone?
As tracked by KanonAgent: 5 upvotes (first indexed 2026-09-21).
What are the best Agent Chaperone alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, taste-skill, archify, open-design, deer-flow, ruflo.