Temporal memory
Keeps original, current, working and historical memory separate but linked.
Project memory for AI agents
SPM is the structured, temporal, verifiable and injectable memory layer for agents and teams.
SPM turns fragmented project knowledge into governed project memory that agents can query, package, inject, share, audit and reuse.
Requirements
Original memory
Truth
Current state
Run context
Working memory
Trace
History
Query
topic:release-readiness tags:mcp,agent
Graph
requirements, current state, policy, handoff
Injection
MCP, API, CLI, governed share
SPM gives agentic teams a durable memory layer for real project work: temporal context, trusted handoffs, governed sharing and reusable context assets.
Built for long-running agent work where requirements, decisions and current state must survive across tools, teams and runs.
Designed to make context portable without losing provenance, safety policy, access history or commercial rights.
Product model
The product value is not more storage. It is continuity: agents can distinguish original requirements from current truth, working notes from history and reusable context from private source data.
Keeps original, current, working and historical memory separate but linked.
Organizes memory by topic and tag so agents can work inside bounded domains.
Connects requirements, decisions, agents, shares, policies and events through queryable relationships.
Builds portable, policy-checked memory packages for MCP, API, CLI and external agents.
Shares context with provenance, safety previews, entitlements, access logs and revocation.
Lets valuable context packs become listed, licensed and distributed with source and usage controls.
Workflow
01
Ingest requirements, decisions, code context, policies, run logs and source material with provenance.
02
Separate memory by temporal layer, topic and tag, then connect related events through graph relationships.
03
Generate context packs that include only the memory a task, agent or team workflow needs.
04
Deliver context to MCP tools, API consumers, CLI workflows or external agents.
05
Verify hashes, enforce policies, inspect access logs, revoke entitlements and preserve audit trails.
Use cases
SPM is strongest when memory must be queried, verified, injected and governed across more than one run or tool.
Keep requirements, architectural decisions, current state and active task context aligned across runs.
Offer agents a controlled memory substrate instead of relying on chat history or oversized prompts.
Package reusable project knowledge as governed context packs for client delivery and support.
Preserve source, access, retention, legal hold and verification data around every memory handoff.
Deployment options
Trust layer
Commercial packaging
Builders and small agent teams
Local or small-team SPM with CLI, MCP, context packs and limited projects.
Product and engineering teams
Hosted dashboard, agent workspace integrations, temporal memory, sharing and governance basics.
Teams with governed agent workflows
Advanced permissions, audit logs, higher quotas, private context sharing and provider budgets.
Security-conscious organizations
SSO, private deployment, BYOK/data-residency direction, legal controls, SLA and support.
Context publishers and buyers
Listings, entitlements, licensing, access history and revenue-share-ready context distribution.
Next step