JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(integrations): shared agent plugin runtimes and native adapters (#7203)

Browse Source
This commit is contained in:
Kartik
2026-09-08 23:32:25 +05:30
committed by GitHub
parent dae67f74f5
commit 73e7b8763a
369 changed files with 31056 additions and 20464 deletions
Download Patch File Download Diff File Expand all files Collapse all files
integrations/claude-code-plugin/skills/forget/SKILL.md
+1 -1
View File
@@ -14,7 +14,7 @@ so it stays unless the user explicitly asks to delete that too.
After the user confirms, run:
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" forget --remote --yes
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" forget --remote --yes
```
If the user also asked to delete the repository's shared project memory, add
integrations/claude-code-plugin/skills/pause/SKILL.md
+1 -1
View File
@@ -11,7 +11,7 @@ anonymous telemetry ping still fires at session start unless
`MEM0_TELEMETRY=false`):
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" pause
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" pause
```
Confirm the new state back to the user, and remind them that already-created
integrations/claude-code-plugin/skills/resume/SKILL.md
+1 -1
View File
@@ -11,7 +11,7 @@ Resume memory capture for this machine.
Run:
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" resume
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" resume
```
Confirm to the user that capture is active again. New sessions record evidence and
integrations/claude-code-plugin/skills/search/SKILL.md
+6 -4
View File
@@ -20,7 +20,9 @@ preferences.
Pass `scope` when the question needs something else: `dir` to narrow the
shared memory to the directory you are working in (a package inside a
monorepo), `mine` for your own preferences alone. Pass `run_id` with a Claude
Code session ID to look at what one earlier session recorded, for example to
pick up where a compacted or closed session left off. Return the tool's result
directly.
monorepo), `mine` for your own preferences alone.
Pass `run_id` with any scope to retrieve memories saved in a specific coding-agent
session. Omit `run_id` to search across sessions. It filters the memories returned;
it does not identify the session making the search request. Use a known session ID,
never invent one. Return the tool's result directly.
integrations/claude-code-plugin/skills/status/SKILL.md
+2 -2
View File
@@ -9,8 +9,8 @@ disable-model-invocation: false
Run both commands and report the combined result in plain language:
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" status --json
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" doctor
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" status --json
python3 "${CLAUDE_PLUGIN_ROOT}/core/memory_cli.py" --harness "claude-code" --plugin-data-dir "${CLAUDE_PLUGIN_DATA}" doctor
```
Summarize, using only fields the JSON actually reports: whether capture is