Debug agent failures in minutes, not hours. Track every LLM call and cost in real-time.
Every LLM call. Every tool execution. Every decision. One stream. Zero guesswork.
You can't see what your agents are doing
LLM costs are invisible until the bill arrives
Observability tools are framework-specific
Install in 15 minutes. Zero code changes.
No code changes. No SDK. Just observability.
// Before const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY }); // After (one line change) const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY, baseURL: "http://localhost:8080/v1" // ← Add this });
Debug in minutes, not hours
Every LLM call, tool execution, and decision:
No more black boxes. Every event is timestamped and logged.
Live feed showing code-reviewer agent: 2 LLM calls, 3 tool executions, 7.1s total, $0.005 cost
Find the bug in 30 seconds
When a run fails, see the exact step:
From "what happened?" to "here's the fix" in one view.
"Before AgentArm, debugging meant grep-ing logs for 2 hours. Now I see the full execution path in 30 seconds."
Execution trace for Run #47: 7-step path with timing and costs per step
Never get surprised by a $2K bill again
Track every dollar:
Catch the $0.003 call before it becomes a $1,000 month.
📊 AgentArm users reduce LLM costs by 23% on average
(by identifying and fixing inefficient prompts)
Last 30 days: $45.23 across 4 agents. Breakdown by agent and provider.
Your data stays on your infrastructure
• Run locally (SQLite)
• Self-host (PostgreSQL)
• Cloud (managed option)
You own your traces.
Row-level security out of the box
• Tenant isolation (PostgreSQL RLS)
• API key authentication
• Audit logs
Production-grade from day one.
Apache 2.0 license
• Full source access
• Community-driven
• No vendor lock-in
Fork it. Extend it. Own it.
Built for production workloads
• Multi-agent support
• High-volume ingestion
• Real-time streaming
Scales with your agent fleet.
Free forever. No credit card required.
"With AgentArm, I can pinpoint agent failures in minutes instead of hours. The real-time event streams and execution traces make debugging so much faster, saving me at least 4 hours a week."
"With AgentArm, I finally have clear cost tracking per agent and run, which means no more surprise costs eating into our budget. It's been a lifesaver in keeping expenses under control while ensuring we meet all the compliance requirements."
"With AgentArm, I finally got rid of my framework lock-in headache. It's so smooth switching between OpenClaw and my custom Python agents without losing any visibility or debug capabilities—it's like night and day."
"With AgentArm, I can finally see exactly what's happening with each LLM call. It helped me cut down our prompt costs by 15% just by optimizing the queries for efficiency."
"With AgentArm, I finally got clear visibility into what our AI agents are doing without needing to dive deep into the code. The real-time event streams and execution traces have been invaluable for explaining performance issues to executives in plain terms."
No. AgentArm adds <5ms overhead per request. The proxy is designed for production workloads and won't impact your agent's performance.
Self-hosted deployment means your data stays on your infrastructure. We never see your prompts, responses, or agent conversations. You own the database.
Yes, when self-hosted. Your data never leaves your infrastructure, meeting HIPAA requirements for patient data protection. Perfect for healthcare applications that need complete data control.
That's exactly what AgentArm is built for. One dashboard for all agents, regardless of framework. OpenClaw, LangChain, CrewAI, custom agents — all in the same feed.
15 minutes from install to first event. Point your agent to localhost:8080, run the proxy, done. No SDK integration, no code changes.
npm install -g agentarm # Or self-host docker run -p 8080:8080 -p 3000:3000 agentarm/proxy
// One line change in your agent code
baseURL: "http://localhost:8080/v1"
Open http://localhost:3000
Watch your first agent run appear in real-time
Install AgentArm in 15 minutes. Watch your first agent run.
Zero cost. Zero lock-in.