Nowledge Mem API
RESTful API Reference for Nowledge Mem.
Health Check
Health check endpoint.
List Communities
List knowledge communities with AI summaries.
Get Community Details
Get community details including entities and sample memories.
List Labels
List all labels with usage counts.
Create Label
Create a new label.
Get Label
Get a specific label by ID.
Delete Label
Delete a label and all its relationships.
Update Label
Update an existing label.
Get Memory Labels
Get labels assigned to a memory.
Assign Label To Memory
Assign a label to a memory.
Remove Label From Memory
Remove a label from a memory.
Toggle Memory Favorite
Toggle memory favorite status.
Toggle Thread Favorite
Toggle favorite status for a thread.
Get Favorite Memories
Get all favorite memories.
Get Favorite Threads
Get all favorite threads.
Search Memories
Memory 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.
Export Memory
Export a memory in various formats.
Preview Memory Kg Extraction
Preview knowledge graph extraction for a memory. This endpoint extracts entities and relationships from a memory's content using the local LLM, pro...
Apply Memory Kg Extraction
Apply knowledge graph extraction results to a memory. This endpoint saves the extracted entities and relationships to the graph database and update...
Reindex Memories Bulk
Reindex multiple memories or all memories needing reindex. This endpoint can work for both single and bulk reindexing: - If memory_ids is provided:...
Get Reindex Status
Get status of memories needing reindex.
Get Search Index Status
Get status of the search index (LanceDB + hybrid search). The embedding model is platform-specific: - macOS Apple Silicon: Qwen3-Embedding via mlx-...
Reindex Search Index
Rebuild the search index from Kuzu database. This performs a full reindex of: - All memories (with search embeddings) - All thread messages - All c...
Get Thread Summaries
Get all thread titles/summaries.
Search Threads Full
Full thread search with message matching.
Save Session
Save coding session(s) as conversation thread(s). Auto-detects sessions from project_path. Creates new thread or appends to existing (with deduplic...
Get Import Config
Get the current import configuration.
Update Import Config
Update import configuration.
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.
Get Watcher Status
Get the current status of the session watcher.
Start Watcher
Start the session watcher for auto-importing sessions.
Stop Watcher
Stop the session watcher.
Discover Conversations
Discover conversation files from AI coding assistants. Scans file system for conversation files from Claude Code, Codex, Cursor, and OpenCode.
Import Conversation
Import a conversation file into Nowledge Mem. Converts external conversation formats (Claude Code, Codex, Cursor, OpenCode) into threads.
Export Conversation Raw
Export a raw conversation file as markdown or JSON without importing. Parses the session file using the same parsers as import, but returns formatt...
Export Thread
Export a thread in various formats.
List Threads
List threads with filtering and pagination.
Create Thread
Create a new thread with messages.
Append Messages To Thread
Append messages to existing thread (for MCP integration). Supports two modes: 1. Direct messages: 2. File-based: Optional controls: - (default: tru...
Get Thread
Get a complete thread with messages.
Delete Thread
Delete a thread and optionally its extracted memories.
Get Thread Coverage
Read-only coverage report for debugging progress issues.
Bulk Delete Threads
Delete multiple threads and optionally their extracted memories.
List Entities
List entities with optional filtering.
Get Entity Relationships
Get relationships for a specific entity. Returns all connected entities and memories via RELATES_TO and MENTIONS relationships.
Distill Memories From Thread
Create memories from thread content after distillation. This endpoint actually creates memories in the database based on the distillation type. For...
Preview Distillation
Preview distillation results without creating memories in the database. This endpoint processes content and returns distilled data for user review ...
Parse Thread Content
Parse thread content from various formats.
Search Graph
Enhanced graph search that finds relevant content and builds visualization data.
Get Graph Data
Get graph data for visualization.
Expand Neighbors
Expand neighbors of a specific node to get connected nodes and edges with depth-based traversal.
Get Graph Analysis
Get comprehensive graph analysis including community and centrality metrics. This endpoint provides a complete overview of the graph structure, com...
Graph Analysis Health
Health check for graph analysis service. Returns the status of algo extension and graph analysis capabilities.
Get Augmentation State
Get the current graph augmentation state. Returns information about which augmentations are currently applied, their parameters, and the last augme...
Start Augmentation Job
Start a background augmentation job. Supports job types: - 'community_detection': Apply Louvain community detection - 'pagerank_calculation': Apply...
Get Job Status
Get the status of a specific augmentation job. Returns job progress, status, and any error messages.
List Augmentation Jobs
List recent augmentation jobs. Optionally filter by status (pending, running, completed, failed).
Find Orphaned Entities
Find all orphaned entities in the graph. Orphaned entities are Entity nodes that have no relationships: - No MENTIONS from any Memory - No RELATES_...
Cleanup Orphaned Entities
Clean up all orphaned entities from the graph. This safely removes Entity nodes that have no relationships: - No MENTIONS from any Memory - No RELA...
Get Bge M3 Status
Check the status of the search embedding model for hybrid search. The model is platform-specific: - macOS Apple Silicon: Qwen3-Embedding (1024-dim,...
Install Bge M3
Download and install the search embedding model for hybrid search. The model downloaded is platform-specific: - macOS Apple Silicon: Qwen3-Embeddin...
Parse Bulk Export
Parse all threads from a bulk export file. This endpoint parses the export file and returns summaries of all threads found. The full thread content...
Import Bulk Threads
Import selected threads from a bulk export. This endpoint starts a background import job and returns immediately. Use the job_id to poll for progress.
Get Import Status
Get the status of a bulk import job.
Get Agent Status
Get the Knowledge Agent's current status.
Trigger Daily Briefing
Manually trigger a daily briefing.
Trigger Crystallization
Manually trigger a crystallization review.
Trigger Insight Detection
Manually trigger proactive insight detection.
Trigger Community Detection
Manually trigger community detection on the knowledge graph.
Trigger Kg Extraction
Manually trigger KG extraction (backfill, targeted, or scoped to specific memories).
Get Knowledge Processing Status
Get knowledge processing settings and status.
Get Working Memory
Read the Working Memory file (~/ai-now/memory.md). Returns today's WM by default, or an archived day's WM if date is provided. This is the single s...
Update Working Memory
Write the Working Memory file from user edits. Validates structure, writes to ~/ai-now/memory.md, and emits a feed event with edited_by='user' to d...
Get Working Memory History
List dates that have archived Working Memory files. Scans ~/ai-now/memory-archive/ for YYYY/MM/YYYY-MM-DD.md files. Returns newest-first.
Get Evolves Edges
Get EVOLVES relationships. Edge direction: older → newer. When memory_id is provided, returns only edges where that memory participates (as either ...
Get Feed Events
Get feed events from time-partitioned JSONL files. Supports two filtering modes: - last_n_days: N days back from today (default) - date_from + date...
Resolve Event
Resolve an action-required feed event and optionally execute graph mutations. Resolution marks the event as resolved in the JSONL file. Action (opt...
Delete Feed Event
Soft-delete a feed event by marking deleted=True in the JSONL file.
Persist Question
Persist a question + agent response as a feed event (JSONL). Called by the frontend after agent streaming completes for questions. Does NOT create ...
Submit Feed Input Stream
Stream agent processing of feed input via Wire Protocol. This is the agent-first approach: the agent classifies input, searches the knowledge base,...
Ingest File
Ingest a file through the full source pipeline. Accepts a multipart file upload. The file is saved to a temp location, then processed through inges...
Ingest File Path
Ingest a file by local filesystem path (desktop app bridge). Unlike the multipart upload endpoint, this accepts a path to a file already on disk. U...
Ingest Url
Fetch a URL and ingest through the source pipeline. Uses browse-now for authenticated content, falls back to httpx.
List Sources
List sources with optional filtering and pagination.
Search Sources
Full-text search across source names and content.
Get Source Detail
Get source detail with related memories and revision chain.
Update Source
Update source lifecycle state. Supported actions: - 'reparse': Re-run parse → chunk → index pipeline - 'mark_stale': Mark source as stale (needs re...
Delete Source
Delete a source and its search index records.
Get Source Content
Read the parsed content of a source for preview. Returns the markdown content produced by markitdown during parsing. Works uniformly for files, URL...
Get Source Image
Serve an extracted image from a source's images/ directory.
Get Source Raw
Serve the raw source file for native preview (PDF, DOCX, etc).
Trigger Source Extraction
Trigger knowledge extraction from a source (Learn lifecycle). User clicks 'Learn' button on a source in the Library. Queues a source_extraction tas...
Refetch Source
Re-fetch a URL source's content using the browser and re-parse. Useful when the initial fetch captured an SPA shell or stale content. Only works fo...