Add Human Context to Your AgentsReal identity data agents can read.
Don't rebuild assessments, parsing, and access controls. Start with the Context API so agents work from a real person, not a prompt that forgets.
Identity as infrastructure
Agents don't need to reconstruct the user on every request. Context is already there.
Readable contracts
Context API first. Stable errors. Clear field definitions. No guesswork.
Continuous action
Agents filter, judge, and move work forward from the same long-term context. Tokens multiply.
Start Here
Quickstart
From API key to first successful request in the shortest path.
Context API
Pull aggregated context first. Expand to task endpoints when needed.
Reference / OpenAPI
Stable contracts, predictable errors, shared definitions for real integration.
Recommended PathRead context first. Go deeper second.
Let agents read long-term context first, then decide if deeper capabilities are needed.
Create an API Key
Call Context API
Expand by Task
Create an API Key
Generate a bearer key and define access boundaries first.
Call Context API
Make profile, preferences, and signals the default context layer.
Expand by Task
Add graph, alerts, and prediction only when the workflow needs them.
Built for Real Workflows
AI Assistants
Answer from a real profile instead of relearning the user each time.
Matching Systems
Plug into matching, ranking, and filtering workflows with user permission.
Automation Workflows
Embed long-term context into notifications, coaching, and recommendations.
Custom Agents
Use ProfileClaw as the memory layer instead of scattering identity across prompts.
Integration Principles
Start with aggregated context before task endpoints
Depend on stable types, not free-form error strings
Keep OpenAPI and docs on the same contract source
Design for agent continuity, not single requests
Build with Real Human ContextRead the docs, wire it into your agents.
Start with docs, review pricing, and decide if you're building for personal workflows or product integration.