memory-gateway/skills/memory-system-api/SKILL.md

name, description

name	description
memory-system-api	Use when an AI agent needs to work with this repository's lightweight Memory System API for OpenViking session memory and EverOS user profiles: starting the API, checking health, writing user/assistant conversation messages, committing or immediately extracting memory, searching memory with hybrid/agentic modes, reading user profiles, or debugging backend partial failures.

Memory System API

Use this skill to operate the lightweight Memory System API from an AI agent. The API hides two backends:

• OpenViking stores session conversation memory.
• EverOS stores user profile and episodic memory.

Prefer this API over direct backend calls unless the user explicitly asks to debug OpenViking or EverOS directly.

Implementation notes:

• The caller never needs to manage OpenViking user keys. The API stores returned user keys locally when OpenViking provides them; if OpenViking reports that an account already exists or does not return a key, the API uses the configured root key with X-OpenViking-Account and X-OpenViking-User identity headers.
• Search responses are sanitized before returning to callers. Large embedding arrays under JSON fields named vector are removed from both merged items and backend debug payloads. Metadata such as vector_model may still appear.

Before Calling

1. Confirm the service is running or start it from the repository root:

python -m memory_system_api.server --config config.yaml --host 127.0.0.1 --port 1934

2. Check health:

curl -s http://127.0.0.1:1934/memory-system/health

3. If server.api_key is set in config.yaml, include X-API-Key on every request.

See references/api.md for request examples and response handling.

Write Conversation Memory

Use POST /memory-system/messages.

Pass:

• user_id: stable end-user ID.
• session_id: stable conversation/session ID.
• user_message: optional.
• assistant_message: optional.

At least one of user_message or assistant_message must be present. If both are present, the backend writes them as two separate messages, in user then assistant order.

Important EverOS rule: assistant messages must not use the user ID as sender_id. The API handles this internally; do not bypass it by calling EverOS directly unless debugging.

Trigger Memory Extraction

Use commit when the conversation turn/session should be finalized:

POST /memory-system/sessions/{session_id}/commit

This runs OpenViking commit and EverOS flush concurrently. OpenViking commit is asynchronous; if the response includes a task ID, check it with:

GET /memory-system/openviking/tasks/{task_id}?user_id=...

EverOS flush may be slower than OpenViking because it can call LLM extraction/rerank services. Treat partial_success as retryable when OpenViking succeeds but EverOS fails; inspect backends.everos.error, wait for the upstream service to recover, then commit the same session again.

Use immediate extract only when the user explicitly asks to remember something now or when validating recent writes:

POST /memory-system/sessions/{session_id}/extract

This wraps OpenViking extract only.

Search Memory

Use POST /memory-system/search.

• use_llm=false: OpenViking find plus EverOS method=hybrid.
• use_llm=true: OpenViking search plus EverOS method=agentic.

The API queries both backends concurrently and returns merged items. Preserve source_backend when presenting or using results so the caller can tell where each memory came from.

The response also includes backends for debugging. Do not expect raw embedding vectors there; fields named vector are intentionally stripped to keep responses small.

Read User Profile

Use:

GET /memory-system/users/{user_id}/profile

This calls EverOS memories/get with memory_type=profile.

Error Handling

Expect status to be one of:

• success: all attempted backends succeeded.
• partial_success: at least one backend succeeded and at least one failed.
• failed: all attempted backends failed.

When partial_success or failed, inspect backends.openviking.error and backends.everos.error. Do not hide backend-specific failures behind the top-level status.

Empty backend exception messages are normalized to the exception type, for example ReadTimeout, so an empty error string should not be expected from current API versions.

Validation

After changing the API or this skill, run:

python -m pytest -q
python -m compileall -q memory_system_api tests
python /home/tom/.codex/skills/.system/skill-creator/scripts/quick_validate.py skills/memory-system-api