Skip to content
ThinkWork ThinkWork

Memory

Memory is the context layer agents use before they act. It is not a single database, vector index, or chat-history trick. It is the ThinkWork-owned layer that decides what an agent should know for the current turn, where each fact came from, how fresh it is, and whether it is durable enough to carry forward.

The clean model is:

  • Threads keep the complete record of work.
  • Memory assembles the context that should matter now.
  • Agents reason and act using that assembled context.

That distinction matters. Threads answer “what happened?” Memory answers “what should the agent know before it responds or takes action?”

What It Contains

Section titled “What It Contains”

Memory is an umbrella over durable Hindsight memory plus source families that can be inspected or lazy-loaded. Operators see them together in Admin because they all affect what an agent can know, but each source keeps its own contract and provenance.

Retained Memory

Durable facts, preferences, and observations retained from prior work. Hosted ThinkWork stores user and Space Brain memory in Hindsight.

Pages

Compiled pages: entity, topic, and decision pages distilled from memory records and source citations.

OKF Wiki Navigator

A generated, read-only linked markdown projection that explicitly enabled Pi runtimes can traverse with bounded wiki tools and visible trace evidence.

Business Ontology

Tenant-governed business types, relationships, facet templates, and mappings that shape durable memory materialization.

Brain Sources

Operator-curated Space documents retained into Hindsight with stable document ids, tags, observation scopes, and source evidence.

Workspace Files

Permissioned files from an agent workspace, template workspace, or tenant defaults.

Approved MCP Tools

Read-only, search-safe external tools that an admin has explicitly allowed to participate in context lookup.

Source Routing

The internal query_context contract that fans out to eligible sources and returns normalized hits plus per-source status.

Why It Exists

Section titled “Why It Exists”

Most agent systems expose memory, RAG, workspace search, and external search as separate tools. That makes agents choose implementation details mid-turn and makes operators debug the wrong layer: was the answer bad because the memory engine missed, the KB was stale, or the agent never called the right tool?

Memory puts those sources behind one operator boundary:

  • operators can inspect and test the sources together;
  • agents can use direct Hindsight memory plus external context without hard-coding every backend;
  • every hit carries provenance, source family, rank, freshness, and provider status;
  • backend choices can change without changing the product story.

How a Turn Uses Memory

Section titled “How a Turn Uses Memory”

At turn time, the runtime combines recent thread history, direct Hindsight memory recall/reflect, compiled pages, Brain Sources, workspace files, and approved external context tools. Context Engine ranks and budgets lazy-loaded external results before the model sees them.

User message arrives in a thread
        │
        ▼
  Turn context assembly
        │
        ├─ Recent thread history
        ├─ Hindsight recall/reflect
        ├─ Compiled pages
        ├─ Brain Sources
        ├─ Workspace files
        └─ Approved MCP search tools
        │
        ▼
  Assembled context → model/runtime
        │
        ▼
  Response + tool calls → thread

Every external source is optional. A focused support bot may only need Space Brain Sources. A long-running sales agent may use Hindsight memory, compiled customer pages, workspace files, and approved operational search tools.

Trust and Provenance

Section titled “Trust and Provenance”

Memory treats source trust as a product concern, not a prompt afterthought.

  • Authored knowledge comes from Hindsight-retained Brain Sources and keeps document/source citations.
  • Memory comes from prior work and keeps Hindsight bank/source references.
  • Ontology defines approved business meaning before it changes durable memory structure.
  • Compiled pages summarize many source facts and keep page-section provenance.
  • External MCP hits are transient unless a separate workflow promotes them.
  • Operational facets can be live and fresh, but should not be silently converted into durable narrative facts.

Admin Surface

Section titled “Admin Surface”

In Admin, the operator Memory surface lives at /settings/memory and has four views:

ViewPurpose
MemoryBrowse and search operator-visible Hindsight memory records with bank evidence
WikiInspect compiled pages and page search output
SourcesManage Hindsight Brain Sources and document ingest
Knowledge GraphInspect ThinkWork Brain graph diagnostics when graph infrastructure is present

Ontology Studio lives under Manage → Ontology because it governs tenant-level business vocabulary rather than one source family. Operators use it to scan for suggestions, review change sets, approve definitions, and monitor reprocess jobs.

Older paths and implementation names may still use knowledge for compatibility, but the canonical operator route for this pass is /settings/memory.

Section titled “Related Pages”