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 — every score is re-derived by the same automated method as an agent's public evidence changes.
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 and capabilities
- 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.