JDSS/mem0

Files

T

kartik-mem0 013718c817 refactor(opencode): native SDK tools, drop MCP, trim skills, expand telemetry

Reworks @mem0/opencode-plugin to expose memory operations as native OpenCode
tools (via the @opencode-ai/plugin `tool()` helper, backed by the mem0ai SDK)
instead of delegating to the remote MCP server. Skills load via the `config`
hook (`skills.paths`) instead of being copied into the project `.opencode/`.

- Drop MCP: remove the regex-based MCP tool interception, the bundled
  opencode.json MCP registration, and the cli.ts installer (mem0-opencode bin).
- Native tools: add_memory, search_memories, get_memories, get_memory,
  update_memory, delete_memory, delete_all_memories, delete_entities,
  list_entities, get_event_status.
- Trim skills 16 -> 8 (context-loader, dream, forget, health, peek, pin,
  remember, tour); remove import, export, memory-reviewer, mem0, list-projects,
  switch-project, stats, onboard. De-MCP/onboard wording in kept skills.
- Telemetry: emit the full shared plugin.* schema (adds user_prompt, bash_error,
  pre_compact, session_stop alongside session_start, tool_use); tool_use now
  fires from inside each native tool; add project_hash + os_version props.
- Fix duplicate error-search (single topK:6); correct the documented
  experimental.chat.messages.transform hook name.
- Bump to 0.2.0.

2026-06-16 12:35:58 +05:30

2.3 KiB

Raw Permalink Blame History

name, description

name	description
pin	Pins or unpins a memory to protect it from pruning during dream consolidation. Use when a memory is critical and must never be removed, such as architecture decisions, security constraints, or immutable team conventions.

Mem0 Pin

Pin a memory to mark it as high-priority and protect from pruning.

Execution

Step 1: Find the memory

The user provides either a search query or memory ID.

If memory ID:

Call get_memory with the ID.

If search query:

Call search_memories with the query, filters={"AND": [{"user_id": "<id>"}, {"app_id": "<pid>"}]}, top_k=5.
Show numbered list with content previews.
Ask: "Which memory to pin? Enter a number."

Step 2: Read current content

Call get_memory with the selected memory ID. Store:

original_text — the memory's text content
original_metadata — the existing metadata dict

Step 3: Pin it

The update_memory tool updates a memory by id. To pin durably, append a pin marker to the text so it travels with the memory:

pinned_text = "[PINNED] " + original_text if not original_text.startswith("[PINNED]") else original_text
update_memory(id=<selected_id>, text=pinned_text)

For new memories (user wants to pin text that isn't stored yet):

Call add_memory with:
- text="[PINNED] <the user's text>"
- user_id=<active_user_id>
- app_id=<active_project_id>
- metadata={"pinned": true, "type": "decision", "confidence": 1.0}
- infer=False
The response contains event_id. Call get_event_status(event_id=<event_id>) once to retrieve the memory ID, then confirm.

Step 4: Confirm

Pinned: "<memory content, first 80 chars>"
Memory ID: <id>

Append ... only if content exceeds 80 characters.

Unpin

If the user says "unpin":

Call get_memory to read current content.

Remove the pin marker from the text:

unpinned_text = original_text.removeprefix("[PINNED] ")
update_memory(memory_id=<id>, text=unpinned_text)

Print: Unpinned: "<content>..."

Output formatting

IMPORTANT: Do NOT use markdown in your output. OpenCode TUI renders text verbatim — markdown like bold, ## headers, and | table | syntax appears as raw characters. Use plain text with indentation for structure. Use dashes for lists. Use spaces to align columns instead of markdown tables.

2.3 KiB Raw Permalink Blame History