MIT License · OTel GenAI SemConv · No signup required

Observe every
agent.
Locally.

Open-source, OTel-native observability for autonomous AI agents. Full telemetry, cost tracking, and safety alerts — on your machine, no backend required.

5 min setup Python + TypeScript OTel SemConv compliant Works with Grafana, Jaeger, Datadog
ocw — bash
quick install
pip pip install openclawwatch
npm npm install @ocw/sdk

Your agent ran.
But did it behave?

Every other observability tool is built for LLM developers. OpenClawWatch is built for people whose agents have real-world side effects.

No visibility into what agents do while you sleep

Agents running overnight have full access to email, files, and services. Without observability, you find out what happened when a customer complains.

Silent cost blowouts

An agent looping on a failing tool call can burn $40/hr. Without per-agent cost tracking, you get the bill at the end of the month.

Every tool requires a SaaS account

Behavioral drift detection, safety alerts, schema validation — they all require API keys, hosted backends, and credit cards. OpenClawWatch runs on your machine.

What OpenClawWatch gives you

Full OTel-native telemetry — agent spans, tool calls, token metrics — conforming to GenAI SemConv, exportable to Grafana or Jaeger
Real-time USD cost tracking per agent, per model, per task — with configurable daily budget alerts
Sensitive action alerts — fires when your agent sends email, writes files, or submits forms, before the session ends
Local behavioral drift detection — catches when agent behavior diverges from its baseline without any cloud dependency
Full-featured CLI + local REST API — pipe to jq, grep, tail, or any tool you already use
Works with OpenClaw, LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, OpenAI Agents SDK, Anthropic (direct), Google Gemini, AWS Bedrock, NemoClaw, or any custom agent

Everything a single developer needs.
Nothing they don't.

OTel-native telemetry

Full GenAI Semantic Conventions compliance from day one. Agent spans, tool calls, token metrics — exportable to Grafana, Jaeger, Datadog, or any OTel backend without transformation.

OTel SemConv v1.37+
Token & cost tracking

Real-time USD cost per LLM call, attributed to the agent and tool that triggered it. Configurable daily/session/per-agent budget alerts fire before you get the bill.

per-model pricing TOML
Autonomous agent safety alerts

The only observability tool built for agents with real-world side effects. Configurable alerts fire on email sends, file writes, form submissions, and payment actions.

unique to OpenClawWatch
Local behavioral drift detection

Deterministic, no-cloud drift detection. Automatically baselines token usage, tool call sequences, output schema, and session duration — alerts when agents deviate.

no API key required
Output schema validation

JSON Schema validation for tool outputs and agent responses. Declare schemas per-agent/tool in config, or use inference mode to auto-derive from observed sessions.

JSON Schema draft-07
CLI + local REST API

A full-featured CLI (ocw status / traces / cost / drift) with JSON output on every command. Local API at localhost with Prometheus /metrics endpoint, OpenAPI spec included.

pipe-friendly · scriptable

Works with every major agent runtime

OpenClaw
LangChain
LangGraph
LlamaIndex
CrewAI
AutoGen
OpenAI Agents SDK
Anthropic (direct)
Google Gemini
AWS Bedrock
NemoClaw
Custom agents

Everything monitoring tells you the agent ran.
OpenClawWatch tells you what it did.

The tools your team already uses are built for LLM developers. OpenClawWatch fills the gap they all leave open.

Feature OCW OSS Langfuse LangSmith Vex Guardrails AI
Observability
OTel GenAI SemConv nativecompliant from day one ~ ~
LLM call tracing
Token & cost tracking
Framework agnostic
Autonomous agent safety
Sensitive action alertsemail, file write, payment, form submit
Cost budget alertsdaily / session / per-agent
NemoClaw sandbox events
Retry loop detection
Runtime verification
Behavioral drift detection API key
Output schema validation
Developer experience
Fully local, no signup
CLI interface
OTLP export to any backendGrafana, Jaeger, Datadog…
Open source / self-hostable
Supported ~ Partial or roadmap Not available API key Requires hosted service

OSS is genuinely useful.
Commercial solves a different problem.

The commercial tier isn't a restriction — it's for teams. Multi-agent aggregation, dashboards, and SSO require cloud infrastructure that is out of scope for a local developer tool by design.

Capability OpenClawWatch OSS ClawWatch Commercial
Telemetry collection✓ All runtimes✓ Via OSS layer
OTLP export (Grafana, Jaeger, etc.)✓ Full export✓ Plus hosted ingestion
Token & cost tracking✓ Single agent✓ Multi-agent + org budgets
Local safety alerts✓ stdout / webhook / file✓ Plus cloud channels
Behavioral drift detection✓ Deterministic, local✓ Plus LLM-as-judge
Output schema validation✓ JSON Schema✓ Plus custom eval rules
CLI interface✓ Full featured
Local REST API✓ localhost✓ Cloud-hosted
Web dashboard & charts— intentionally excluded
Multi-agent aggregation— out of scope
SSO / RBAC
LLM-as-judge evaluation
Hosted retention & search

Want the commercial tier? → cla.watch

Early access

Be first to run it.

OpenClawWatch is in active development. Join the waitlist to get early access, shape the roadmap, and get notified when v0.1 ships.

✓ You're on the list. We'll be in touch.

No spam. Just a ping when we ship. MIT Licensed.