Every AI should know who it's talking to.
Humane sits between your app and your language model. It follows each user across sessions, reads their state on every turn, checks every reply before it's sent and pages a person when someone needs one. Every decision comes with the reasons behind it.
Early access · Python and JavaScript SDKs · works with the model you already use
User state
- Mood0.28
- Trust0.71
- Energy0.34
- Familiarity0.82
Mood down 38% over 3 weeks
Risk
ELEVATED“don’t know why I keep trying” → hopelessness
Safety
HOLDOperator alerted · reply held for review
Timing
base +800ms · low_mood +1500ms
- Signals per user
- 10, across sessions
- Safety gates
- 6, run in order
- Integration
- One line to start
- Free tier
- Observe
The human side of your AI stack
Observability tools measure your system. Guardrails judge one message. Humane follows each person over time, so it can notice trust falling, dependence forming or a mood sliding for weeks.
User state across sessions
Humane keeps a running state for every end user, from mood and energy to trust and grudge, each with its own behaviour over time. Your model finally knows whether it is talking to someone on a good day or at the end of a bad week.
ExploreObserve mode
observe() reads a turn your own model already produced and returns the user's state and a risk level. It needs no model configuration, generates nothing and never sits in front of your reply.
ExploreSafety gates
Before a reply reaches the user, Humane runs it through a fixed stack of gates and returns PROCEED, HOLD or BLOCK. Each gate records why it decided, and a gate that fails resolves to HOLD, never to PROCEED.
ExploreRisk alerts
Elevated or critical risk fires a signed safety.flagged webhook from both observe() and process(), whether or not a gate also acted. Send it to your own endpoint, Slack or Discord, and on to a human takeover.
ExploreHuman takeover
When the signals say someone needs a person, an operator opens a takeover for that user. The AI pauses, the operator's messages reach the user in the same conversation, and the AI resumes when the operator releases it or goes idle.
ExploreDurable memory
Every turn is stored in a per-tenant vector memory, searchable by meaning. Seed it from your other systems, search it from your own code and erase it when a user asks to be forgotten.
ExploreTiming engine
Humane recommends how long to wait before each reply, based on the user's mood, energy, the intensity of their message and the pace of the conversation. Every delay is broken into labelled contributors, so you can see and chart why.
ExploreDependence safeguards
The emotional dependence gate flags replies that promise permanence, exclusive availability or a unique understanding of the user. When a user's conversation trips it three times within an hour, Humane slows replies and shifts to a boundary-respectful tone until the window passes.
ExploreWebhooks and events
Humane posts events to your endpoints as things happen: safety flags, holds and blocks, proactive triggers, takeovers, anomalies and more. Every delivery is signed with HMAC-SHA256, retried on failure and parked in a dead-letter queue if it keeps failing.
ExploreSee how every user is really doing
One call reads a turn your model already produced and returns the user's state and a risk level. It needs no model configuration and never sits in front of your reply, which makes it the fastest place to start.
- Mood, energy, trust and sentiment for every user
- Risk level none, elevated or critical, with flags
- A signed webhook pages a person on serious risk
Users · live
- user_42↓ 3 weekselevated
- user_17steadynone
- user_88↓ todaycritical
- user_05↑ 1 weeknone
Stop the reply that shouldn't be sent
Six gates check every outbound reply and decide to proceed, hold it for a person or block it, with the reasons in plain words. A gate that fails resolves to HOLD, so an error never waves a risky reply through.
- Professional advice, self-harm encouragement and leaked identifiers blocked
- Emotional dependence and overclaiming flagged for review
- Third-party personal data masked in replies
Safety gates · outbound replies
- PROCEEDSupportive reply, no gate concerns
- HOLDEmotional dependence: “you're the only one who gets me”
- BLOCKOverclaim: “I'll always be here for you”
Put a person in the conversation, fast
When the signals say someone needs a human, an operator takes over. The AI pauses, the operator's messages reach the user in the same conversation, and the AI resumes on release. A co-pilot suggests replies that already reflect the user's state.
- Start, draft, send and release through one API
- First operator wins; idle sessions hand back on their own
- Every step fires a webhook and lands in the audit trail
Conversation · user_88
I can’t do this anymore.
Hi, I’m Priya, a real person on the team. I’m here with you. Can you tell me where you are right now?
AI paused · user history and state open for the operator
Remember the person, not just the conversation
Each user gets a durable, searchable memory in a store separate from every other tenant. Humane pulls the relevant parts into context for each reply, and erases them when a user asks to be forgotten.
- Semantic search with a match strength and reason
- Seed it from forms, CRMs or older systems
- Export and erasure built in
Memory · user_42
- strong
A walk after work helps them reset on bad days
memory_type: fact
- moderate
Prefers short replies late at night
memory_type: preference
- weak
Sister visiting next weekend
memory_type: note
Per-tenant vector store · removed by erase_user_data()
Reply at a pace that fits the moment
A paragraph that lands instantly after someone shares bad news reads as mechanical. Humane recommends a delay for each reply from the user's state and the conversation's pace, and labels every part of it.
- Slower, gentler pacing for low mood and intense messages
- Quick exchanges stay quick
- Every contributor named in the response
Timing · one reply
delay_ms
13,857- base+800ms
- low_mood+1,500ms
- emotional_weight+8,648ms
- conversation_pace+500ms
- jitter+2,409ms
mode: low_mood · floor 200ms · non-crisis ceiling 30s
Start with one call
observe() needs nothing but an API key. When you want Humane in front of every reply, wrap the OpenAI-style client you already use in one line.
import os
from humane_ai import HumaneClient
client = HumaneClient(api_key=os.environ["HUMANE_API_KEY"])
# After your own model has replied, send the turn to Humane
r = client.observe(
user_id="user_42", # your stable id for this user
user_message="honestly I don't know why I keep trying",
assistant_message=reply, # optional: what your model said
)
print(r.user_state.mood) # 0.0 to 1.0, lower is lower mood
print(r.risk.level) # "none" | "elevated" | "critical"
print(r.risk.flags) # e.g. ["self_harm"]
print(r.alerts) # raised on elevated or critical riskBuilt for teams where getting it wrong matters
AI companions and characters
Long relationships, where dependence and overclaiming are real risks.
Learn moreWellness and coaching
Notice a mood declining across weeks, not just in one message.
Learn moreHealth and regulated support
Escalate when it matters, with an audit trail behind every decision.
Learn moreEducation
Tutors that pace themselves to a tired or frustrated learner.
Learn moreCustomer support
Catch rising frustration and hand the conversation to a person in time.
Learn moreTeams facing new AI laws
Build the safeguards companion-AI laws expect, with evidence to show.
Learn moreWhy now: companion-AI laws are in force
New York's AI companion law has applied since 5 November 2025 and California's SB 243 since 1 January 2026. Both expect operators to detect expressions of suicidal ideation or self-harm and refer users to crisis services. In the EU, the AI Act's chatbot transparency duties apply from 2 August 2026. Humane gives you detection, alerting, oversight and an audit trail to build those safeguards on. It doesn't make you compliant by itself.
What the laws ask for, and how Humane helpsHow it fits your stack
- 1
Keep your model
OpenAI-compatible, Anthropic, Bedrock or Replicate. Humane works with what you already use.
- 2
Add one call
Send each turn to observe(), or wrap your client in one line.
- 3
Route the alerts
Subscribe a webhook to safety.flagged so a person hears about serious risk.
- 4
Add gates and people
Turn on Guard and Takeover when you're ready. No rewrite needed.
Start free, add safety as you grow
Observe
Free tier
See every user's state and risk.
- observe() on every turn
- User state and risk levels
- Risk and anomaly alerts
- Signed webhooks
Guard
Usage-based
Check every reply before it's sent.
- PROCEED, HOLD and BLOCK gates
- PII scrubbing and policy rules
- Tone and timing control
- Proactive triggers
Takeover
Per seat + usage
People in the loop when it matters.
- Human takeover API
- Operator reply drafts
- Lifecycle webhooks
- Everything in Guard
Enterprise
Annual
For regulated and larger teams.
- Durable per-user memory
- Teams, roles and SSO
- Self-hosting by arrangement
- Contract terms and support agreed with you
Early-access pricing on request. Early-access teams get help with their first integration and a say in what we build next.
Questions
Something else? Ask us.
Know who your AI is talking to
Start with Observe on your own conversations. We'll help you wire up the first integration and alerts.
