AgentHippo
See what your agents do. Cut cost. Ship faster.
Local-first observability for AI agents. Traces, token cost, and tool loops in VS Code — no cloud, no sign-up.
Use your existing subscriptions: Claude, Codex, Cursor, ChatGPT.
⟩ What developers say
"Finally I can see where my agent spend goes. Spotlight panel + traces in one place."
"Using Claude and Codex in the same flow with one observability layer. Game changer."
"Local-first traces and cost. No cloud sign-up. Exactly what we needed for our team."
"Finally I can see where my agent spend goes. Spotlight panel + traces in one place."
"Using Claude and Codex in the same flow with one observability layer. Game changer."
"Local-first traces and cost. No cloud sign-up. Exactly what we needed for our team."
"The agent-built charts in Spotlight are exactly what I asked for. No fixed dashboards."
"Cut our API spend by seeing tool loops and prompt bloat. AgentHippo made it obvious."
"The agent-built charts in Spotlight are exactly what I asked for. No fixed dashboards."
"Cut our API spend by seeing tool loops and prompt bloat. AgentHippo made it obvious."
⟩ Get started
Full IDE and CLI. Use your existing Claude, Codex, or ChatGPT subscription.
Install AgentHippo →Free to start. No sign-up for local use. Pricing
⟩ Built for agent observability
See every run, every token
Traces, token cost, and tool loops in one place. Know exactly what your agents did and what they cost—no cloud required.
Learn about traces →
Spotlight: analytics in your language
A flexible dashboard where your agent creates the charts. Ask in natural language; get custom visualizations from trace data—cost trends, session breakdowns, ad-hoc reports.
Explore Spotlight →
Full IDE and CLI, your platform
Agent Hippo is a standalone IDE (like Cursor) plus a CLI binary. Same observability on Mac, Windows, and Linux x86 or ARM.
Install Agent Hippo →
⟩ What you get
Spotlight panel
A flexible analytics dashboard where agents create the charts. Ask in natural language; your agent generates custom visualizations from trace data—cost trends, session breakdowns, ad-hoc reports. No fixed dashboards.
Traces & cost
Every run, every token, in one place. See exactly what your agents did and what they cost.
Agent-native
Tool loops, prompt bloat, cost-per-outcome—not just per-request. Built for how agents actually work.
Your engines, your subscriptions
Power agents with free or paid OpenAI (Codex), ChatGPT, Claude, Cursor, or any LiteLLM-compatible API. One observability layer across all of them.