Meet Helm

A dedicated Mind for every agent.

Give your AI agents a place to remember, connect knowledge, and build on past work. Keep the context when the conversation ends.

Your own dedicated instance. Start free.

A little context changes everything

Made to remember.

The conversation ends.
The context stays.

The decisions. The details. The thread of an idea.
Six kinds of memory. One continuous Mind.

Explore memory

Meet Helm / The Minds Operator

Your next move.
Just say it.

Start a dedicated Mind through a conversation with Helm.
Clear choices, a visible action, and a result you can inspect.

HelmFrom intent to action
Create a Mind for our support team.

Helm

Let's give your team a Mind. Start with a region and a name.

New Mind
Demo workspace
  1. 2Name & create
Where should it run?
What should we do next?
Creation flow demo · No account changes

Your workspace. One conversation away.

Talk to Helm

One engine

Store it once.
Put it to work.

Akasha, the engine behind Minds, brings records, similarity search, connected facts, and SQL analytics together. Give your application several ways to use the information it keeps.

Akasha engine

The join path connects kv, vector, graph, sql through one Minds engine to joined context. This diagram illustrates a data flow; it does not display live traffic.

Use SQL to ask structured questions across supported data sources.

Illustrated flow

Six kinds of memory.
One continuous Mind.

A past conversation is different from a password or a reusable workflow. Minds gives each kind of information a place, so your agents can use it for the right task.

Sample memory
Launch journalSeptember
DecisionSep 09 · 14:30
The team chose one shared workspace for the first release.
review-notes.md

Remember what happened.

Record the events, decisions, and outcomes that matter. Your agent can return to saved experience and the sources you attach.

  • Events in order
  • Original sources
  • What mattered and how it felt
Explore episodic memory
Reasoning

Break down the question.
Work through the evidence.

Give your agent a way to plan smaller steps and connect pattern matching with rules and known relationships. Minds provides reasoning tools you can configure around your task, with paths you can inspect.

hrm://reasonExample
goalWhy did Q3 revenue dip?
Plan
Decompose the revenue question
Pull revenue by channel · Q3
Diff against the Q2 baseline
4Localize the mix shift
5Form causal hypothesis
6Draft recommendation
Current step
$ vector.recall(similar dips, k=8)
matches Q3-2024 pattern
Confidence0.94
ACT · halt
ACT · depth 4 / 6
ns://fusionExample
query
> Why did Q3 revenue dip?
1
Find patterns0.87
2
Check relationships0.92
3
Combine the evidence0.94
path4 triples
RevenueQ3
Q3Paid
Paid−18%
PaidQ3-2024
NsClient.findPaths
Knowledge Graph

Connect the facts. Keep their history.

Connect people, projects, and events so your agent can follow relationships. When a fact changes, keep both when it changed and when the update arrived.

graph://bitemporalExample
Alice
Paper
Model
Dataset
Fact
Agent
Claim
Obs
t_valid · 2025-09-30
Facts · 4
Spiking Neurons

Understand events as they unfold.

A spiking neural network processes signals over time. Build applications that look for patterns in sensor readings, market ticks, or logs, where the timing matters.

snn://raster· t=24Example
InputLIF
HiddenIzh.
Outputadaptive
26
in window
28
example neurons
48
time steps

The platform at a glance

Built around the way your agents work.

Explore the engine ↗
0
kinds of memory

Experiences, workflows, resources, secrets, working context, and patterns.

0
ways to work with data

Records, vector search, a knowledge graph, and SQL analytics in one engine.

0
dedicated Mind

Your own instance, with the same Mind when you upgrade from Free to Pro.

0
ways to get started

Talk to Helm, connect an SDK, or work from the command line.

Evaluation

Put memory to the test.

Useful memory has to return the right context. Explore how to inspect retrieval and understand what an evaluation measures, from the questions asked to the method used to judge the results.

Governance · Lineage

See where an answer came from.

Knowledge lineage records how a claim was formed and which sources contributed to it. Follow that trail to inspect the evidence before you rely on the result.

Illustrated lineage7 nodes · 4 depths
00Sources

Original records

01Extract

Identify the evidence

02Reconcile

Evaluate the result

03Belief

Keep the source trail

Selected belief

Q3 revenue ↓ 12%

Depth 3 · Derivation · 4d ago

The revenue claim completes this illustrated trace. Follow its derivations back to the interview and the filing that contributed to it.

Original sources
Build with Minds

Save context. Put it to work.

Bring a saved decision into the next request. These examples search existing memories from your application or terminal. The HTTP examples use a Mind with MCP enabled. Set AKASHA_URL to its endpoint, AKASHA_TOKEN to its bearer token, and AKASHA_CAPABILITY to an issued capability token authorized for the operation.

Example · retrieve a saved project decision
const capability = process.env.AKASHA_CAPABILITY;
if (!capability) throw new Error("Set AKASHA_CAPABILITY before connecting");

const response = await fetch(
  new URL("/v1/mcp/tools/call", process.env.AKASHA_URL),
  {
    method: "POST",
    headers: {
      Authorization: "Bearer " + process.env.AKASHA_TOKEN,
      "x-akasha-capability": capability,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      name: "recall",
      arguments: { query: "What release schedule did we choose?", limit: 5 },
    }),
  },
);
if (!response.ok) throw new Error("Memory request failed: " + response.status);
const output = await response.json();
if (output.is_error) throw new Error("Memory tool failed");
console.log(output.result.memories);
TypeScript
Typed client
Python
Synchronous client
cogs CLI
Scripts and operations
control-room
Interactive terminal
Estimate

See what more capacity would cost.

Choose a compute size, how much data you keep, and how much you transfer each month. Free has capped usage. Pro starts at $29; larger sizes and usage beyond the included amounts add to the cost.

Compute sizeMicro (fixed)

Free includes the Micro compute size. Upgrade to Pro when you need more capacity.

Storage (GB)1 GB
Transfer (GB / month)5 GB
Capabilitiesmemory included
Storage · Memory
Estimated · Free · Micro
$0/ mo

A dedicated Micro instance with capped storage and transfer.

Free · Micro instance$0
Compute · Micro (fixed)included
Storage · 1 / 1 GBincluded
Transfer · 5 / 5 GBincluded
Engine capabilitiesincluded
Start free in chat

Every Mind is dedicated. This estimate covers compute size, storage, and transfer; capability selections do not change the estimate. Model-provider usage and separately contracted integrations are outside this estimate. Engine services may require configuration or training.

Pricing

Start free. Grow with the same Mind.

Start with a dedicated Mind. Upgrade to Pro for more capacity, with pricing based on compute, storage, and transfer. Engine access is included; model-provider usage and separately contracted services are outside these resource prices.

Free
$0/ month
Your own dedicated Mind to get started. Storage and transfer are capped. If you reach a limit, your Mind pauses until you upgrade.
Engine capabilities included
  • Dedicated Micro instance
  • Capped usage
  • 1 GB storage
  • 5 GB transfer/mo
  • Engine capabilities included
  • Upgrade to Pro keeps the same instance
Start free
For growing projects
Pro
$29/ month
More capacity for growing projects, starting at $29 a month. Upgrade the same Mind and pay for compute, storage, and transfer beyond what your plan includes.
Engine capabilities included
  • Base compute size
  • Larger compute sizes available
  • 25 GB storage
  • 50 GB transfer/mo
  • Additional compute, storage, and transfer at published rates
  • Engine capabilities included
Upgrade to Pro
Enterprise
Custom
Plan a deployment on private infrastructure, with terms and support shaped around your team.
Private deployment and custom terms
  • Private infrastructure deployment planning
  • Data processing agreement by arrangement
  • Service-level commitments by agreement
  • Deployment and integration support planning
Talk to us
Your memories are yours.

Keep your knowledge in a dedicated Mind. Read how Minds processes account and service data, and how connected providers may handle your requests. How we treat your data

Built for continuity

Thenextconversationshouldstartwithcontext.

A useful conversation should leave something behind: a decision, a source, a better way to do the work. Give your agents a Mind to carry that context into whatever comes next.