Manifest
Real-time cost observability for OpenClaw agents: track tokens, actions, and spend with self-hosted deployment and alerts.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Manifest, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
Manifest is an AI agent observability tool focused on cost transparency for OpenClaw agents. It provides real-time token and cost tracking across agents and actions, helping teams identify expensive tasks and runaway context before bills spike. Manifest emphasizes privacy by collecting telemetry metadata rather than prompts/messages, and it supports self-hosted deployment so data can remain inside your network. It also includes notifications and thresholds to alert you when an agent approaches or exceeds spending limits.
Key features
- cost observability
- token tracking
- telemetry
- opentelemetry
- otlp
- alerts
- self-hosted
- usage analytics
- spend monitoring
Use cases
- Tracking token usage and spend per agent, per message, and per action in real time.
- Finding the most expensive workflows to optimize prompts, models, and tool usage.
- Setting cost thresholds and receiving alerts when spend spikes or exceeds limits.
- Running observability on your own infrastructure to keep agent data inside your network.