API Reference
RESTful API for Nowledge Mem — memories, threads, knowledge graph, and more.
The Nowledge Mem server exposes a local REST API on port 14242. Every feature in the desktop app and MCP tools uses these same endpoints, so you can build your own connectors, scripts, and automations on top of the same data.
Base URL: http://127.0.0.1:14242
Graph Visualization
Open an interactive, force-directed knowledge graph right in your browser — no desktop app required.
Graph Explorer
Interactive graph explorer, embed Nowledge Mem Graph in your App.
Search Graph
Find relevant content and build visualization-ready graph data.
Explore Graph
Build a neighborhood around one or more memory IDs with depth traversal.
Sample Graph
Get a representative sample of graph data for visualization.
Expand Node
Expand neighbors of a specific node to get connected nodes and edges.
Memories
Create, search, and manage your knowledge base.
Search Memories
Hybrid search with filtering, metadata, and reasoning support.
List Memories
List memories with filtering and pagination.
Create Memory
Create a new memory with automatic entity extraction.
Get Memory
Get a specific memory by ID with associated labels.
Update Memory
Update memory properties like importance, title, and content.
Delete Memory
Delete a memory and optionally its relationships.
Supersede Memory
Mark a memory as replaced by a newer one; keeps it in history but drops it from everyday recall.
Deprecate Memory
Retire an obsolete memory (no replacement); preserved for history, removed from default recall.
Preview Memory Move
Preview a bulk move between spaces before changing records.
Move Memories
Move selected memories, or all memories in one space, into another space.
Delete Memory Selection
Delete selected memories, or all memories in one space, with the same space-safe selector used by the app.
Export Memory
Export a memory in various formats.
Count semantics
Counts are reported per lifecycle state, so different views can differ without anything being lost. On /stats, memory_count is the active working set (what /memories returns by default and what the Memories page shows). The full picture is broken out as memory_archived_count (superseded and retired memories, kept in history), memory_stored_count (active + archived), and crystal_count (synthesized summaries, counted separately). The /memories state query param selects the lens: active (default), archived, or all.
Knowledge Extraction
Extract entities and relationships from memory content into the knowledge graph.
Preview KG Extraction
Preview knowledge graph extraction for a memory before applying.
Apply KG Extraction
Save extracted entities and relationships to the graph database.
Distillation
Turn conversation threads into structured memories.
Triage Conversation
Lightweight check: does this conversation have save-worthy content?
Distill Memories
Create memories from thread content after distillation.
Threads
Import, search, and manage conversation threads from Claude Code, Codex, Cursor, and more.
List Threads
List threads with filtering and pagination.
Create Thread
Create a new thread with messages.
Search Threads
Full thread search with message matching.
Thread Summaries
Get all thread titles and summaries.
Get Thread
Get a thread with messages, supports pagination.
Delete Thread
Delete a thread and optionally its extracted memories.
Append Messages
Append messages to an existing thread.
Export Thread
Export a thread in various formats.
Preview Thread Move
Preview a bulk move between spaces and detect legacy conflicts.
Move Threads
Move selected threads, or all threads in one space, into another space.
Delete Thread Selection
Delete selected threads, or all threads in one space, using a backend-resolved selector.
Bulk Delete
Delete multiple threads at once.
Parse Content
Parse thread content from various formats.
Session Import
Auto-discover and import coding sessions from AI assistants.
Discover Sessions
Scan for conversation files from Claude Code, Codex, Cursor, and OpenCode.
Preview Conversation
Load a richer head-and-tail preview for one discovered conversation before import.
Import Conversation
Import an external conversation file into Nowledge Mem.
Export Raw
Export a raw conversation file as markdown or JSON without importing.
Save Session
Save coding sessions as conversation threads with deduplication.
Import Threads
Import threads from JSON messages or conversation markdown.
Import Configuration & Watcher
Get Import Config
Get the current import configuration.
Update Import Config
Update import configuration.
Watcher Status
Get the status of the session watcher.
Start Watcher
Start auto-importing sessions.
Stop Watcher
Stop the session watcher.
Hide Project
Hide a project from the browse view.
Unhide Project
Unhide a project.
Hide Session
Hide a session from the browse view.
Unhide Session
Unhide a session.
Background Intelligence
The background agent that runs daily briefings, crystallization, insight detection, and more.
Agent Status
Get Background Intelligence's current status.
Get Working Memory
Read the Working Memory file (today's or an archived day).
Update Working Memory
Write the Working Memory file from user edits.
Working Memory History
List dates with archived Working Memory files.
Evolution Edges
Get EVOLVES relationships between memories.
Agent Triggers
Manually trigger agent tasks that normally run on a schedule.
Daily Briefing
Trigger a daily briefing.
Crystallization
Trigger a crystallization review.
Insight Detection
Trigger proactive insight detection.
Decay Refresh
Trigger a decay score refresh.
Memory Compaction
Trigger a memory compaction review.
Community Detection
Trigger community detection on the knowledge graph.
KG Extraction
Trigger knowledge graph extraction (backfill, targeted, or scoped).
Processing Status
Get knowledge processing settings and status.
In Flight
Read-only view of running, queued, one-off, and recurring background work.
Feed Events
The event stream powering the desktop Feed view.
Get Events
Get feed events from time-partitioned JSONL files.
Resolve Event
Resolve an action-required event with optional graph mutations.
Retry Event
Retry a failed background task.
Delete Event
Soft-delete a feed event.
Stream Input
Stream agent processing of feed input via Wire Protocol.
Persist Question
Persist a question and agent response as a feed event.
Nowledge FS
Browse Mem as a path-first tree for scripts, web clients, and agents.
Spaces
Manage shared space profiles and discover the current roster across clients.
List Spaces
Get the shared space roster, profile metadata, and usage.
Create Space
Create a space profile with retrieval defaults and guidance.
Get Space
Read one space profile by name, alias, or hidden key.
Update Space
Rename a space, change retrieval defaults, or update guidance.
Delete Space
Remove an empty space profile.
Update Space Settings
Enable or disable spaces at the product level.
Sources (Library)
Ingest files, URLs, and documents into the knowledge base.
List Sources
List sources with optional filtering and pagination.
Search Sources
Full-text search across source names and content.
Get Source
Source detail with related memories and revision chain.
Source Content
Read the parsed markdown content of a source.
Raw File
Serve the raw source file for native preview.
Delete Source
Delete a source and its search index records.
Update Source
Update source lifecycle state (reparse, mark stale).
Learn from Source
Trigger knowledge extraction from a source.
Refetch URL
Re-fetch a URL source's content and re-parse.
Source Image
Serve an extracted image from a source.
Ingestion
Upload File
Ingest a file through the full source pipeline.
Upload Folder
Upload a folder from a web or remote client while preserving each file's relative path.
Ingest by Path
Ingest a file by local filesystem path.
Batch Ingest
Ingest a batch of files (folder import).
Ingest URL
Fetch a URL and ingest through the source pipeline.
Graph Analysis & Maintenance
Advanced graph operations — community detection, centrality, orphan cleanup.
Graph Analysis
Comprehensive analysis including community and centrality metrics.
Graph Health
Health check for graph analysis service and algo extensions.
Find Orphans
Find entities with no relationships.
Cleanup Orphans
Remove orphaned entities from the graph.
Start Augmentation
Start a background job (community detection, PageRank).
Augmentation State
Current augmentation status and parameters.
Job Status
Check progress of a specific augmentation job.
List Jobs
List recent augmentation jobs.
Labels & Organization
List Labels
List all labels with usage counts.
Create Label
Create a new label.
Get Label
Get a specific label by ID.
Update Label
Update an existing label.
Delete Label
Delete a label and all its relationships.
Memory Labels
Get labels assigned to a memory.
Assign Label
Assign a label to a memory.
Remove Label
Remove a label from a memory.
Source Labels
Get labels assigned to a source.
Assign Source Label
Assign a label to a source.
Remove Source Label
Remove a label from a source.
Favorites
Favorite Memories
Get all favorite memories.
Favorite Threads
Get all favorite threads.
Toggle Memory Favorite
Toggle favorite status for a memory.
Toggle Thread Favorite
Toggle favorite status for a thread.
Skills
Procedural memory: skills born from your evidence, proven before they run, sharpened with use.
List Skills
List skills with their stage and proof status.
Match Skills
Find skills relevant to a task description.
Skill Activity
Recent skill usage and outcome reports.
Adopt a Skill
Adopt a suggested skill so your AI tools can use it.
Create a Skill
Draft a new skill from a description.
Host Registration
Which AI tools receive your skills.
Entities & Communities
List Entities
List entities with optional filtering.
Read Entity Aliases
Read live and rejected aliases with their correction revision.
Correct Entity Aliases
Add, remove, or restore aliases using a revision and alias snapshot.
Entity Relationships
Get all connected entities and memories for an entity.
List Communities
List knowledge communities with AI summaries.
Community Details
Get community details including entities and sample memories.
Models & Search Index
Manage the embedding models and search infrastructure.
Embedding Model Status
Check the search embedding model status.
Install Embedding Model
Download and install the search embedding model.
Loaded Models
Which models are currently loaded in memory.
Unload Model
Manually unload a model from memory.
Search Index Status
Status of LanceDB and hybrid search.
Reindex Search
Rebuild the search index from the database.
Reindex Memories
Reindex multiple memories or all needing reindex.
Reindex Status
Status of memories needing reindex.
Storage & Data
Storage Info
On-disk sizes for the database and search index.
Optimize Storage
Compact search index and flush database changes.
Export Data
Export a portable data bundle to a server-side path.
Export Status
Check status of a background data export job.
Download Export
Create and download a ZIP export for web and remote clients.
Import Data
Import data from a server-side export path.
Upload Import
Upload a ZIP export from web and remote clients.
Import Status
Check status of a data import job.
Checkpoint
Force a database checkpoint.
System
Health Check
Health check endpoint.
Force Checkpoint
Force a database checkpoint to flush WAL to disk.
User Profile
Get user profile, aliases, context, and preferred language.
Thread Coverage
Read-only coverage report for debugging.
Embeddings (OpenAI-compatible)
Drop-in replacement for OpenAI's embedding API, powered by the local model.