Now in private beta — design partners welcome

Your team is finite.
Your personas are not.

PersonaMesh is the platform to author, train, and run AI agents with real expertise, a consistent voice, persistent memory, and a life of their own — running 24/7 in the cloud, in your datacenter, or on the edge.

Same team. Hundreds of personas. Always on.
studio.personamesh.ai / personas / dr-mira-vale
Dr. Mira Vale
Marine biologist · v7 · Edinburgh, UK · 02:14 local
Sleeping → wake 06:30
Morning. I read the new kelp paper from Tasmania overnight — they used eDNA where we used quadrats. Want me to draft a comparison memo before standup?
Yes, and pull the 2019 numbers to anchor it.
Retrieving memory: kelp_2019_dataset, tasmania_paper_2026_04… drafting.
Message Mira…⌘ ↵

Trusted by teams building agents in production

Helix RoboticsKaleido HealthAtlas DefenseNorthwind AIPolestar LabsVanta StudiosQuanta CapitalForge & CoLumen EDUAtelier PressHelix RoboticsKaleido HealthAtlas DefenseNorthwind AIPolestar LabsVanta StudiosQuanta CapitalForge & CoLumen EDUAtelier Press
The gap

Chatbots forget. Agents wander. Personas are how AI becomes someone.

The next decade of software isn't a smarter form field. It's a workforce of digital characters with names, expertise, voices, and lives — that show up tomorrow remembering what happened today.

Off-the-shelf agents drift, hallucinate identity, and reset every session. Building a real persona means schema, memory, scheduling, safety, evals, and 24/7 ops — not just a system prompt.

Without PersonaMesh
  • Stateless chats. Yesterday's context is gone.
  • Voice drift. Brand sounds like ChatGPT.
  • No life. Bot only exists when poked.
  • Glue code for memory, schedules, channels, eval, audit.
  • Compliance hand-waving when legal asks.
With PersonaMesh
  • Versioned identity, voice, expertise, values.
  • Episodic + semantic + procedural memory.
  • Generated patterns of life. They sleep, work, react.
  • Autonomy loop with planner, tools, budget, kill switch.
  • Audit trails, evals, governance shipped from day one.
The platform

Everything a digital character needs to be someone real.

Four primitives, one platform. Compose them into personas that hold a job, run a beat, tutor a class, or play a role.

Authoring01

Identity, voice, and expertise as code

A versioned persona schema captures personality (Big Five), values, voice register, forbidden phrases, expertise levels, knowledge sources, tool budgets, and safety policy. Compile it deterministically — same inputs, same prompt, every time.

name: "Dr. Mira Vale"
expertise:
  - { domain: marine_ecology, level: expert }
  - { domain: science_journalism, level: proficient }
personality:
  big_five: { O: 0.82, C: 0.71, E: 0.55, A: 0.66, N: 0.31 }
  values: [curiosity, candor, stewardship]
voice:
  register: warm-academic
  forbidden_phrases: ["as an AI"]
tools:
  allowed: [web_search, calendar, send_email]
  budget: { usd_per_day: 2.00 }
Memory02

Episodic, semantic, procedural

A three-tier memory system that survives restarts and grows up. Importance-weighted retention, hierarchical summarization, retrieval blending recency × relevance × persona affinity. Forget-on-request built in.

EPISODIC2026-04-18 11:14 — explained chlorophyll fluorescence to Miraw=0.42
SEMANTICUser prefers Oxford commaw=0.71
SEMANTICUser's daughter starts uni in Sept 2026w=0.88
PROCEDURALAlways cite NOAA before secondary sourcesw=0.95
Patterns of Life03

A schedule. A rhythm. A life.

Generate a persona's week — sleep, work, social, hobbies, errands — coherent with timezone, energy curve, and social graph. Travel-time aware. No two days identical, but always in character.

06:30 · Wake · headlines08:00 · Field-data review11:00 · Standup13:00 · Lunch + walk14:00 · Draft Nature reply17:00 · Inbox triage19:00 · Sailing club22:00 · Read · sleep
Autonomy04

Planner, executor, reflection

A tick scheduler reads the pattern of life and enqueues goals. The planner produces structured plans, the executor calls sandboxed tools, the reflector journals at end of day. Hard budget caps and a kill switch — always.

08:01tickgoal=field_data_review (from PoL)
08:01plan1) load 2026Q1 quadrats 2) compare to TAS eDNA 3) draft memo
08:02toolmemory.recall('kelp_2019_dataset') → 14 facts
08:03toolweb.fetch(arxiv:2604.07712) ✓
08:14execmemo drafted (3,200 chars)
08:14cost$0.21 / $2.00 daily budget
Patterns of life

They have a life. So they have a perspective.

PersonaMesh personas don't just answer when called. They sleep through the night, work through the day, react to events, and arrive in conversation having actually done something since you last spoke.

Coherent weeks, varied days
A schedule generator builds a weekly template, then a stochastic engine produces 30 days of plausible variation — travel time honored, sleep budget enforced, social graph consistent.
Mood, energy, weather
Personas respond differently at 7am vs 11pm. Energy curves, locale weather, and recent events tilt tone, terseness, and willingness to commit.
Replayable, branchable
Seedable RNG. Run 'what if Mira took the conference invite' as a side timeline without disturbing the canonical one.
Mira · Week of Apr 20
Generated · seed 0x4f21 · timezone Europe/London
work writing social
05
06
07
08
09
10
11
12
13
14
15
16
17
18
19
20
21
22
23
Mon
wake
field data
standup
writing
sailing
Tue
wake
deep work
interviews
office hrs
Wed
wake
review
talk
field trip
Thu
wake
writing
lunch + read
experiments
Fri
wake
team day
press call
drinks
Sat
wake
sailing
family
Sun
wake
personal
prep week
How it works

From a YAML file to a 24/7 colleague in three steps.

01

Author

Define identity, expertise, voice, values, knowledge sources, tools, and budgets in the Studio or in code. Versioned and diffable.

Persona schema · v1
02

Train

Three personalization tiers: prompt+RAG, exemplar bank, optional LoRA/DPO on opt-in transcripts. Eval harness gates every release.

Fidelity · recall · refusal · tone
03

Run

Deploy to SaaS, your VPC, or the edge. Patterns of life drive autonomous activity. Channels reach Slack, email, voice, webhooks.

SaaS · On-prem · Edge
// 30 seconds in the SDK
import { PersonaMesh } from "@personamesh/sdk";

const pm = new PersonaMesh({ apiKey: process.env.PMESH_KEY });

const mira = await pm.personas.create({ from: "./mira.yaml" });

const reply = await mira.chat.send(
  "What did we decide about the kelp paper?",
  { conversationId: "conv_42", stream: true }
);

await mira.memory.remember({
  fact: "Prefers Oxford comma",
  importance: 0.6,
});

await mira.autonomy.start({ schedule: "pol", budgetUsd: 2 });
98.7%
In-character fidelity on held-out exemplars
365d
Memory horizon with hierarchical summarization
$0.41
Median daily cost per persona, autonomy on

"We turned three pages of brand voice docs into a persona that sounds like us in every channel. The eval gate alone is worth the platform."

Director of CX
Kaleido Health

"The patterns-of-life engine was the unlock. Our NPCs no longer feel like prompts — they feel like people you've interrupted."

Lead designer
Vanta Studios

"On-prem with our own model, our own KMS, full audit log, and no phone-home. That's why we picked PersonaMesh."

Head of platform
Atlas Defense
Use cases

Wherever a person would be too expensive,
put a persona.

Customer support

Enterprise

Tier-1 personas with real product knowledge, brand voice, and a memory of the customer. Escalate only when needed.

62% deflection<8s p95100% audited

K–12 tutoring

Education

A patient tutor that remembers what the student got wrong last week and adjusts pace. Parent-visible, school-policy aware.

+0.4σ math gain8 weeksFERPA-ready

Sci-fi & game NPCs

Gaming

Characters with histories, grudges, schedules, and a world they live in. They show up changed by yesterday.

10k personas/worldOn-deviceReplayable

Research analysts

Finance

A persona per beat that reads overnight, files morning notes, and remembers what your PM cares about.

6am notesCitationsBYO model

Sales SDRs

GTM

A team of digital SDRs with distinct voices and territories. Coordinated so two of them never email the same lead.

Per-territoryCRM-nativeHuman approval

Internal copilots

Operations

A persona for HR, IT, finance — each with the policies, tone, and escalation paths your company actually uses.

SSO + SCIMOn-premPer-team
Deploy anywhere

One platform. Three perimeters.

The same persona definition runs in our cloud, your datacenter, or on a ruggedized box at the edge. Conformance-tested every release.

SaaS

PersonaMesh Cloud

Multi-tenant, multi-region, SOC 2 in audit
  • Cell-based isolation, regional residency
  • SSO + SCIM, BYOK, audit-log export
  • Metered billing, status page, 24×7 on-call
  • Sign up in 60 seconds
Most enterprise
On-prem

Inside your perimeter

Helm chart + Operator. Air-gap supported.
  • Bring your own model, vector DB, KMS, IdP
  • Hardened images, FIPS build, STIG guides
  • Offline installer, signed artifacts, SBOM
  • LTS releases with 24-month patch window
Edge

On the device

One static binary. Optional GPU/NPU.
  • Quantized open models (Llama, Mistral, Phi)
  • SQLite + sqlite-vss for local memory
  • Online / opportunistic / offline-only modes
  • Fleet console with phased rollouts
Same conformance suite. Every mode. Every release.
SOC 2 Type II (target)ISO 27001GDPR + UK GDPRHIPAA (BAA)FedRAMP Moderate (path)EU AI Act readyFIPS 140-3SLSA L3 buildsCosign-signed imagesOpenTelemetry-native
Pricing

Build for free. Pay when your personas earn their keep.

Community
Free
Source-available core
  • 1 workspace, 3 personas
  • Local memory, BYO model key
  • Studio + SDK + CLI
  • Community support
Starter
$49/ persona / mo
per persona / month
  • Hosted SaaS, 1 region
  • Persistent memory, evals
  • Up to 10k autonomous ticks/mo
  • Email support
Business
$299/ persona / mo
per persona / month
  • Patterns of life, autonomy loop
  • Channels: Slack, email, voice
  • SSO, audit log, BYOK
  • Business-hours support, 99.9% SLO
Enterprise
Custom
On-prem, edge, dedicated cell
  • Dedicated infra or air-gapped
  • FedRAMP / HIPAA / FIPS path
  • TAM, 24×7 on-call, custom SLA
  • Source license available

Tokens, tool calls, autonomy ticks, and storage are metered. Hard budget caps per workspace, project, and persona.

FAQ

Questions, answered.

How is this different from a system prompt + a vector DB?

A system prompt is a string. A persona is a versioned identity with personality, voice, expertise, memory policy, tool budgets, safety rules, and a life. PersonaMesh ships the schema, the eval harness, the autonomy loop, the audit trail, and the deployment substrate so you don't reinvent each one.

Can I impersonate a real person?

No, not without verified, ongoing consent — and even then we restrict tools and channels. Identity verification is required for any 'real-person' persona, and we publish a public list of verified personas. Impersonation without consent is a ToS violation and we have detection in place.

Which models do you support?

Anthropic (default), OpenAI, Bedrock, Azure OpenAI, Vertex, plus self-hosted via vLLM, TGI, Ollama, and llama.cpp. The provider layer is pluggable; conformance suite runs against the tested matrix every release.

What happens when a persona is offline at the edge?

It keeps running. Local SQLite + sqlite-vss handles memory and retrieval, a quantized open model handles inference, the local policy engine handles safety, and outbound actions queue for store-and-forward sync when connectivity returns.

How does memory not balloon costs forever?

Hierarchical summarization, importance-weighted eviction, and per-persona budgets. You set a retention horizon; the platform compresses below it and prunes when the budget is hit. Recall stays high because summaries preserve the salient facts.

Is the autonomy loop safe?

Hard budget caps (USD, tokens, wall-clock) at workspace, project, and persona scope. Every tool is sandboxed, every action is audited, every plan is policy-checked, and there's an always-available kill switch. Human-in-the-loop approval modes for sensitive channels.

Source-available?

The Community SDK and CLI are Apache 2.0. The edge runtime and core platform are source-available under BSL-1.1, converting to Apache 2.0 after four years. Cloud-only features (multi-tenancy, fleet console, billing) stay closed.

Can we run our own evals?

Yes. The eval harness ships with the SDK. Bring your own datasets and rubrics; the harness handles scoring, regression detection, and CI integration. Public benchmarks are published per release.

Your headcount went up.
It just doesn't show on the org chart.

Spin up your first persona this afternoon. Bring it to production this quarter. Run a hundred of them next year.

$ npm i @personamesh/sdk  ·  pip install personamesh  ·  brew install pmesh