Memorylayer exposes a hosted service surface around the Engram engine: workspace API keys, agent bootstrap, an HTTP MCP bridge, downloadable starter skills, and regular JSON endpoints for the memory lifecycle.
Status, search, remember, recent memory, audit history, usage tracking, and bootstrap.
One authenticated endpoint for 60 Engram tools with argument hints.
Markdown skills for Codex or Claude-style memory workflows.
Private routes accept Authorization bearer tokens or X-API-Key headers.
Load workspace URLs, starter skills, MCP tools, and OpenAPI links before wiring clients.
Search, remember, ingest, recent memory, usage, audit, and export are regular JSON endpoints.
Use `/mcp` for recall_context, handoff, decisions, entity pivots, and curation tools.
These endpoints are intentionally unauthenticated because they describe the service, not a workspace's private memory.
GET /api/service/manifest
Public route map, counts, and service metadata.
GET /api/capabilities
Capability groups, features, and recipe definitions.
GET /api/mcp/manifest
Tool groups, argument hints, auth headers, and workspace URL templates.
GET /api/sdk-snippets
Copyable JavaScript, Python, shell, ingest, and manifest client examples.
GET /api/playbooks
Workflow checklists for handoff, cleanup, onboarding, and investigation pivots.
GET /api/examples
Request and response fixtures for service discovery, MCP calls, ingest, usage, and export.
All workspace API routes accept a workspace key in either `Authorization: Bearer` or `X-API-Key`.
Use one workspace call to discover the rest of the integration surface.
These are the main hosted routes an agent or service uses day to day.
GET /api/workspaces/{slug}/status
Workspace memory counts and graph stats.
GET /api/workspaces/{slug}/connect
Workspace-specific client profile with endpoints, startup calls, skills, and MCP config.
GET /api/workspaces/{slug}/env
Plain text environment variables for local agents and scripts.
GET /api/workspaces/{slug}/agent-config
Codex TOML, Claude skill markdown, env output, endpoints, and starter curl commands.
GET /api/workspaces/{slug}/codex.toml
A workspace-scoped profile for local launchers and Codex-side boot scripts.
GET /api/workspaces/{slug}/claude-skill.md
A markdown skill that teaches Claude-style agents the workspace startup and shutdown routine.
POST /api/workspaces/{slug}/search
Run hosted retrieval without touching the underlying Engram runtime directly.
POST /api/workspaces/{slug}/remember
Store new narrative, fact, or procedure memories.
POST /api/workspaces/{slug}/ingest
Batch import pasted text, JSON items, or pipeline output into workspace memory.
POST /api/workspaces/{slug}/ingest/preview
Preview split count, sample chunks, and size before writing memory.
GET /api/workspaces/{slug}/memories/recent
Load the last memories written to the workspace.
GET /api/workspaces/{slug}/audit
Inspect workspace-level key usage and memory activity.
GET /api/workspaces/{slug}/usage
Read per-key API activity, route counts, and the latest service calls.
GET /api/workspaces/{slug}/observability
Read latency, p95, failure rate, slow routes, runtime cache, and recent ingest runs.
GET /api/workspaces/{slug}/ingest/runs
Inspect source names, item counts, actors, and timestamps for imports.
GET /api/workspaces/{slug}/export/recent
Export recent workspace memories as JSON for backups or inspection.
POST /api/workspaces/{slug}/mcp
Call selected Engram tools through one hosted bridge.
The batch ingest API accepts either an `items` array or a text `content` field with a split mode: auto, paragraphs, lines, markdown, csv, single, or json.
Copyable requests for the main hosted flows.
The hosted bridge exposes the agent-safe Engram surface: retrieval, handoff, skill selection, curation, and workspace health.
Tool groups are included in the public MCP manifest and the workspace tool discovery response.
7 tools
10 tools
10 tools
8 tools
7 tools
16 tools
Return workspace-level memory counts and graph stats.
Check memory indexes, cache state, and workspace runtime health.
Build a high-level map of layers, entities, and recent memory activity.
Return storage quality, curation, and retrieval quality metrics.
Count memories by layer, source type, entity, or month.
Show which memories and entities are recalled most often.
Report whether the deep retrieval reranker is trained and available.
Run the main Engram retrieval flow against the workspace.
Return a compact context block for prompt injection.
Return short memory hints that trigger recognition without flooding context.
Load the most recent memories for the workspace.
Return facts, relationships, and timeline for a named entity.
Retrieve memories filtered by fact, procedure, or narrative type.
Retrieve memories from one memory layer.
Retrieve memories from a date range.
Traverse related memory context from an entity.
Return retrieval results with scoring and query expansion details.
Fuzzy-search entity names for lookup and disambiguation.
Return a JSON subgraph for a named entity.
Return one entity's memories ordered by date.
Find memories that reference or link to a memory.
Find memories semantically similar to a memory.
Generate a brief about the most relevant memory context for a task.
Return L0-L3 graduated context for system prompt injection.
Select the most relevant procedural skills for a task.
Store a new memory in the workspace.
Store an explicit decision and rationale.
Store an error pattern with prevention guidance.
Store a durable question-and-answer exchange.
Store explicit negative knowledge about what does not exist or should not be done.
Update project-level state for the workspace.
Read the current session diary.
Append a concise entry to the current session diary.
Persist a checkpoint note plus recent state for resumable agent sessions.
Build or save a structured handoff snapshot for another agent/session.
Load the latest handoff snapshot and related recent activity.
Identify dense or high-interest areas in the memory graph.
Compare how two queries retrieve and overlap.
Export workspace memories as markdown or JSON.
Return a compressed summary of retrieved memories for a query.
Attach an operator note to a memory without changing its content.
Edit a memory's content and re-embed it.
Mark a memory as no longer true.
Move a memory through active, challenged, invalidated, merged, or superseded states.
Return lifecycle history for a memory.
Add or remove tags on a memory.
Pin a memory so retention jobs keep it.
Soft-delete a memory from the workspace.
Promote a memory to a higher layer.
Demote a memory to a lower layer.
Remove a pin from a memory.
Manually link two memories through their entities.
Add an alias or metadata to an entity.
Merge one entity into another.
Add tags to memories matching a search query.
Find and merge near-duplicate memories by similarity.
Detect entity communities and optionally generate summaries.
Run a dream cycle to cluster, summarize, and generate peer cards.
Extract reusable procedural patterns from recent activity.
Summarize the current session from diary and recent events.
These skills are available as JSON or plain markdown for agent bootstrapping.
Use the hosted workspace memory service for project recall, remember, and recent context.
Capture the minimum high-value handoff state before stopping work.
The full capability index tracks 254 service, site, and agent features.
Each workspace receives its own Engram schema and service boundary.
User identity is handled through GitHub OAuth with no local passwords.
Issue shareable invites with role-aware membership records.
Generate workspace keys for agents, apps, and ingestion pipelines.
Track service calls by route, key, and workspace.
Record workspace actions such as keys, invites, memory writes, and bridge calls.
Call selected Engram tools through a simple HTTP JSON bridge.
Discover URLs, headers, tools, and skills from one workspace endpoint.
Download markdown skills that teach agents how to use hosted memory.
Load the latest workspace memories without custom query code.
Run hosted retrieval against the real Engram memory graph.
Store narrative, fact, and procedure memories over HTTP.
Bridge tool support for durable decisions and rationale.
Bridge tool support for structured project state.
Generate compact task context from the memory graph.
Find dense or high-activity regions in workspace memory.
Compare retrieval overlap between two prompts or topics.
Expose the machine-readable API contract for clients.
Run a warm Python service with direct Postgres access.
Keep app metadata and Engram workspace data in Postgres.
Search and inspect workspace memory from the browser.
Store memories manually when an operator needs to pin state.
Revoke workspace API keys without touching the memory store.
Keep setup, endpoints, bridge tools, and skills documented in-app.
Import pasted notes, transcripts, reports, or logs directly from a workspace.
Upload a text, markdown, JSON, or CSV-like file and split it into memories.
Push many memories in one authenticated request.
Track source, type, item count, and actor for each ingestion run.
Preview split counts, sample chunks, and payload size before writing memories.
Split imports by headings, rows, lines, paragraphs, JSON items, or one memory.
Download recent workspace memories as JSON for inspection or backup.
Generate workspace-specific client config, env blocks, and startup calls.
Expose a normalized JSON profile that agents can read on boot.
Generate a workspace-scoped TOML profile for Codex-side launchers.
Generate a workspace-specific markdown skill for Claude-style bootstrapping.
Return a copyable .env block for local workers and agent launchers.
Expose latency, failures, slow routes, top routes, runtime cache, and ingestion history.
Ship a repeatable archive-over-SSH deploy path for the VPS service.
Document the shortest path from workspace key to working agent memory.
Explain the hosted runtime, service metadata, workspace schemas, and Engram boundary.
Show practical memory workflows for coding agents, teams, incidents, research, and automations.
Document key rotation, audit review, ingestion hygiene, and incident checks.
Describe how Codex, Claude, custom agents, CI jobs, and scripts connect to hosted memory.