Docs

Memory & Vault

Agent context windows are temporary. Agenties keeps project memory on disk so work can continue across restarts, new sessions, and long-running projects — regardless of which interface or AI assistant you used to give the original instruction. Obsidian and NotebookLM are optional knowledge layers; the operational source of truth stays in the project under .agenties/.

Memory layers

LayerPath or providerPurpose
Operational truth.agenties/Issues, goals, agents, sessions, shared state, reports, and audit trail.
Recent continuity.agenties/continuity/journal.mdChronological log of recent meaningful work.
Context map.agenties/continuity/index.mdCompact map of important decisions, fixes, and where to read more.
Knowledge vaultObsidianHuman-readable doctrine, research, decisions, and summaries.
Semantic facts.agenties/memory/facts.jsonAuto-extracted durable facts from closed issues and agent events.
Semantic recallNotebookLMOptional fuzzy lookup over summaries and research material.
Note:For the full startup and continuity flow, see Continuity System.

Local project files

Agenties writes durable operational context into the project. These files are designed for machines to update and for humans to inspect when needed.

FileUse
.agenties/shared/state.jsonCurrent objective, active agents, open work items, and recent decisions.
.agenties/issues.jsonBacklog and status of project work.
.agenties/goals.jsonMulti-issue execution plans and goal status.
.agenties/reports/*.mdDesign, QA, audit, and continuity reports.
.agenties/team/*/memory.mdPer-team-member memory.

Obsidian vault

Obsidian is the human-readable knowledge layer. Use it for doctrine, decisions, session summaries, research, and project notes. Do not use it as a replacement for `.agenties/` operational state. See Obsidian for the full integration guide.

Recommended vault layout
<your-vault>/
  <project-name>/
    index.md
    decisions/
    doctrine/
    goals/
    issues/
    agents/
    integrations/
    sessions/

Vault MCP tools

ToolDescription
read_vault_noteRead one note by relative path.
write_vault_noteWrite or overwrite a note.
append_vault_noteAppend to a note.
list_vault_notesList notes under the project vault folder.
search_vault_notesSearch notes with bounded excerpts and result caps.
build_init_contextBuild startup context from shared state, continuity files, and vault excerpts.

NotebookLM

NotebookLM is optional. Treat it as semantic recall or research support. It should receive summaries and curated material, not raw operational dumps. See NotebookLM for the full integration guide.

Session commands

CommandDescription
/initLoad minimal project context into the orchestrator.
/wrapupWrite a session summary and prepare the next session.
/vaultOpen or inspect vault notes.
/memoryShow shared state and recent memory.

Memory drawer

The Agenties desktop app includes a Memory drawer in the chat interface. It surfaces the most relevant local memory files — shared state, continuity journal, and vault excerpts — so you can inspect what context agents are working from without leaving the chat. Open it from the toolbar during any session.

Semantic Memory

Agenties automatically extracts durable facts from completed issues and agent task-done events and writes them to .agenties/memory/facts.json. These facts persist across restarts, letting future sessions recall what was decided, what integrations are active, and what risks were flagged — without relying on live Claude context.

Facts are categorised automatically based on content keywords. You can also append facts manually via the append_fact MCP tool.

Fact categories

CategoryWhen used
decisionArchitecture choices, migration decisions, or key direction changes.
issue_resultDefault for closed issues — what was built or fixed.
project_factStable facts about the project (integrations, versions, configurations).
user_preferenceConventions and preferences that should persist ("always", "never").
integration_stateActive third-party integrations and their status.
riskKnown risks, vulnerabilities, or technical debt.
next_stepDeferred work or follow-ups captured across sessions.

MCP tools

ToolDescription
query_factsSearch facts by keyword, category, or scope. Returns most recent first.
append_factWrite a new fact. Duplicate detection prevents duplicate entries.
Note:Facts are also surfaced in the Activity timeline and injected into the orchestrator startup context under "Recent Facts". Prefer query_facts for historical decisions over re-reading shared state.

Automatic triggers

The sidecar hooks into two events to extract facts without manual intervention:

TriggerWhat is extracted
Issue closed (status → done)Issue title + first 200 chars of description, tagged with issueId.
Agent emits task-done with summaryFirst 300 chars of the summary, tagged with agentId and issueId.

Scopes

Each fact has a scope field. Most auto-generated facts use project scope. Valid values: project, session, agent, user, global.


Knowledge Graph

Graphify builds a semantic index of your codebase stored at.agenties/graphify/<slug>/graph.json. Agents use it as a fast pre-search before broad file scans. The graph is separate from vault memory and does not replace it — vault notes are human-authored knowledge, the graph is an auto-built file index.

ToolDescription
graph_statusCheck if the graph is installed and how fresh it is.
graph_queryAsk a natural-language question and get ranked file pointers.
graph_updateRebuild the graph index after major codebase changes.
Note:See Knowledge Graph for full installation and usage details.
Tip:Keep live chat context light. Durable memory belongs in `.agenties/`, the continuity files, and the vault.