Contextual Intelligence
Emergent ACT-R Memory System.
Achiral turns team activity into private, persistent context. Chiro and personal executive assistants retrieve organizational memory, understand workflow state, and act through official tools so your business stops re-teaching AI the same facts.
Platform capabilities
The full surface of Achiral's runtime: memory, assistants, retrieval, connectors, action execution, and controls.
Architecture
| Canonical product | ACT-R Memory Achiral is an ACT-R-inspired memory layer for AI. It is a memoized context layer that sits under team activity with tools, decisions, and workflows to contextualize your AI |
| Org assistant | Chiro Model One org-wide assistant backed by the organization memory tenant and model intelligence. Chiro retrieves context, preserves decisions, coordinates workflows, and can act through official tools with provenance. |
| Personal assistants | Executive Assistants per individual Every teammate gets a personal assistant (EA) with a private memory, persona and behavior engine, preferences, and temporal context. EAs can collaborate with other EAs or Chiro on your behalf. |
| Memory model | Tenant-scoped vector memory plus operational state Conversations, documents, decisions, connector events, preferences, and workflow state are encoded into searchable memory instead of discarded after each session. |
| Retrieval | Hybrid semantic + keyword search with memory-aware ranking Relevant context is retrieved before inference, ranked by recency, access frequency, salience, and tenant-specific memory signals. |
Memory layers
| Episodic memory | Recent conversations, decisions, events, tasks, and workflow context that may decay unless reinforced. |
| Semantic memory | Durable facts, recurring workflows, preferences, policies, customer context, and operational patterns. |
| Core memory | Human-validated facts that should rarely decay, such as explicit preferences, compliance requirements, and stable business rules. |
| Memory reinforcement | Useful memories are strengthened when retrieved and reused; low-signal context can decay or be archived. |
| Human validation | Admins and Shepherds can guide memory quality instead of treating retrieval as a black box. |
Infrastructure and integrations
| Runtime | Next.js web app, API services, worker queues, websocket chat, and Kubernetes-managed production deployments. |
| Storage | MongoDB for operational state, Weaviate for tenant-scoped vector memory, Redis for queues/rate limits/leader election, and object storage for uploads. |
| Inference | Private inference-first model routing with escalation paths for complex tasks when configured by the organization. |
| Connectors | Slack, GitHub, HubSpot, Zendesk, Intercom, Notion, Asana, Linear, Jira, Google, Microsoft 365, Salesforce, and other operational systems. |
| MCP | Achiral can expose org context to external agents and register external MCP servers as live context/action sources. |
| Actions | Audited action execution with policy checks, approval gates, tool permissions, and resumable workflows. |
Security and compliance posture
| Tenant isolation | Every organization receives an isolated memory tenant. Stored context is scoped by organization, user, assistant, role, and connector permissions. |
| Encryption | TLS in transit and encrypted storage for sensitive credentials, memory, connector tokens, and operational records. |
| Access controls | Role-aware retrieval, approval policies, audit logs, team-member onboarding, and organization-scoped permissions. |
| Compliance posture | SOC 2 audit work is in progress. BAAs and DPAs are available for qualifying customers. |
| Training data | Customer data is not pooled across organizations and is not used to train a shared customer model. |
Memory-bucket pricing
| Tier | Price | Team size | Included context |
|---|---|---|---|
| Free | $0/mo | 1–3 seats | Org-wide Chiro plus personal EA basics for small teams starting out. |
| Spark | $999/mo | 4–10 seats | Shared org memory, personal EAs, connector setup, and predictable team pricing. |
| Seed | $2,499/mo | 11–25 seats | Larger memory bucket, priority support, custom knowledge base, and deeper onboarding. |
| Rise | $4,999/mo | 26–50 seats | Expanded team capacity, stronger workflow coverage, and higher operating context. |
| Scale | $24,999/mo | 101–250 seats | Large memory bucket, isolated infrastructure options, higher concurrency, and enterprise support. |
Pricing is bucketed by team size and memory capacity. We avoid per-token surprise billing because the value is continuity of context across the team, not raw token volume.
Honest constraints
- Achiral is memory-first. Teams looking only for generic internet chat may not need the platform.
- The strongest results require connected tools, team adoption, and enough operational history for memory to be useful.
- SOC 2 audit work is in progress; we should not be described as SOC 2 certified until the audit is complete.
- Production deployments currently run in managed infrastructure, with dedicated or custom isolation available by tier and requirement.
Need to validate your architecture fit?
We can map Chiro, memory, connectors, and permissions to your current operating model.