This directory is the single source of shared memory behavior for Mem0 coding-agent plugins. Installable plugins remain ordinary sibling directories under integrations/.

Architecture

integrations/
├── agent-plugin-core/       # Shared source; never installed as a plugin
│   ├── python/              # Claude-derived capture, recall, MCP, scoping, and telemetry
│   ├── typescript/          # Shared lifecycle, formatting, identity, scoping, and telemetry
│   ├── skills/              # The source for six memory skills and the handoff command
│   ├── build/               # Bundle builder, schemas, and validation
│   ├── conformance/         # One offline/live verification entry point
│   └── tests/
├── mem0-agent-plugin/       # One portable Agent Plugins v1 package
├── claude-code-plugin/      # Native Claude package and adapter
├── cursor-plugin/           # Native Cursor package and adapter
├── codex-plugin/            # Native Codex package and adapter
├── kimi-plugin/             # Native Kimi package and adapter
└── antigravity-plugin/      # Native Antigravity package and adapter

Each native directory owns only its manifest, native hooks or adapter, tests, and plugin-build.json. Its core/ and skills/ directories are generated from this module. They are committed because clients install a self-contained plugin directory and the Agent Plugins specification forbids package files from resolving outside the plugin root.

Claude Code remains the behavioral source of truth. Its sidekick stays at claude-code-plugin/agents/sidekick.md and is not generated or copied to hosts without a compatible native subagent interface.

TypeScript integrations (openclaw, opencode-plugin, pi-agent-plugin, and deepseek-plugin) import typescript/src/ at build time. Their package builders include the shared implementation in their normal output; they do not carry checked-in copies.

Shared memory behavior

The six Python packages use the same search_memories MCP tool and six memory skill templates plus the handoff command. Native hooks collect conversations and flush them to Mem0 in the background. The portable package uses the Agent Plugins v1 layout so compatible hosts can load its MCP server and skills. It has no lifecycle hooks or flush worker; its bundled remember skill assumes automatic capture and cannot save a memory on its own.

Search guidance follows Memo: use a focused question when earlier work could help, reuse available context, and search again only for a specific remaining gap. The TypeScript hosts import one shared guidance constant; conformance checks keep it aligned with the generated Python MCP description and reject strict before-answer or repeated-search prompts. Automatic recall schedules and retrieval limits are independent of this wording.

Python search accepts query, top_k, category, scope, and optional run_id:

Scope	Memories searched
`repo` (default)	Shared repository memories and your personal memories in that repository
`dir`	Shared memories from the current directory and its children, plus your personal repository memories
`mine`	Your personal memories in that repository

run_id filters any scope to memories saved in a known coding-agent session. Omit it for recall across sessions; it does not attribute the search request to the current session. Native Python extraction writes include the session's run_id.

New Git repository writes use a hashed remote identity for shared agent_id. Search and explicit shared-memory deletion include both that ID and the legacy unhashed ID under the same app_id. Legacy memories remain accessible, but their original ambiguity between matching owner/repository names on different Git hosts remains.

Captured prompts and responses preserve their full text after secret redaction. Python extraction splits oversized input across requests without dropping message text. The session-end worker flushes the conversation already collected by hooks without adding the final answer again. Search queries, retrieved context, and tool evidence have separate limits.

TypeScript hosts reuse redaction and lifecycle utilities but retain their own tools, scopes, and capture events. They do not inherit the Python repo/dir/mine contract or its background batching. OpenCode captures selected user prompts; Pi and DeepSeek capture completed conversation turns; OpenClaw selects recent messages and earlier summaries, then filters noise. Removing message-length truncation does not turn these integrations into complete transcript archives.

For installation, follow the host guides: Claude Code, Cursor, Codex, Kimi, and Antigravity.

Session handoff

python/session_handoff.py is the common entry point. python/handoff_sources.py reads native transcript formats; python/claude_to_codex.py retains the Claude parser and the single implementation of validation, private recovery, assets, context limits, and Codex import. It is adapted from mem0ai/memo.

The TypeScript hosts read their native active context and use typescript/src/handoff.ts to normalize messages and pass a mem0.session-handoff.v1 bundle to the same Python engine over stdin. OpenClaw supplies its trusted native transcript path. Native Python and portable plugins generate the shared handoff skill, with source-specific instructions.

The common bundle contains source (host, session_id, title, cwd, optional path), items (user/assistant messages, paired function calls/results, and supported images), and optional warnings. The engine derives counts and validates the bundle. Unknown model-visible content, missing tool results, and opaque compaction state fail rather than disappearing from the imported task. Handoff runs only on explicit user request, independently of memory hooks and the Mem0 API. Creation requires Python 3.11+ and a local Codex CLI with native session import support.

build/handoff-runtime.json declares the runtime files once. Every TypeScript build uses build/package_handoff.mjs to package them. Conformance checks reject missing or stale copies, as well as generated Python bundle drift. When the importer changes, regenerate the Python bundles and rebuild the TypeScript packages; no per-plugin importer edits are needed. A new host needs only a native context reader or adapter producing the common bundle.

See the handoff guide for host commands, verified formats, current-session limits, and recovery.

Build and verify

From the repository root:

python3.11 -m venv /tmp/mem0-agent-plugins
/tmp/mem0-agent-plugins/bin/pip install \
  -r integrations/agent-plugin-core/requirements-dev.txt

for host in claude-code cursor codex kimi antigravity; do
  /tmp/mem0-agent-plugins/bin/python \
    integrations/agent-plugin-core/build/build.py "$host" \
    --kind native --check
done

/tmp/mem0-agent-plugins/bin/python \
  integrations/agent-plugin-core/build/build.py mem0-agent-plugin \
  --kind portable --check

Use --sync instead of --check after changing python/ or skills/. This only replaces generated core/ and skills/ content; it does not change manifests, adapters, tests, or the Claude sidekick.

Run every offline Python and TypeScript check and write one machine-readable report:

/tmp/mem0-agent-plugins/bin/python \
  integrations/agent-plugin-core/conformance/run.py \
  --install \
  --report /tmp/mem0-plugin-conformance.json

For every TypeScript integration, this also builds the publishable package, verifies its required entry files, and rejects compiled artifacts that still import monorepo source. This keeps published plugins self-contained without committing their dist/ directories.

The offline suite does not contact Mem0 Platform. An explicit disposable key enables the inherited live scoping suite:

export MEM0_API_KEY="m0-disposable-test-key"
/tmp/mem0-agent-plugins/bin/python \
  integrations/agent-plugin-core/conformance/run.py \
  --group live-platform --live \
  --report /tmp/mem0-plugin-live-conformance.json

Do not put a real key in source files, command history shared with others, or pull-request configuration.

Add a plugin

For another native Python host:

Add integrations/<host>-plugin/ with its native manifest and the smallest adapter that translates host events.
Add plugin-build.json declaring the plugin-root variable and runtime files.
Add one adapter contract test.
Register the host in build/build.py and conformance/run.py.
Run --sync, --check, and the conformance command above.

Keep capture, recall, memory scoping, redaction, skill text, and telemetry in this shared module. Host directories should contain only behavior required by their native SDK.

For a TypeScript host, import the shared lifecycle modules directly and keep only native SDK registration in the integration. Do not advertise capture, compaction, or sidekick behavior unless the host exposes the necessary lifecycle seam.

Host capture capabilities

Host	Conversation capture	Tool outcomes	Subagent context and correlation
Claude Code	Incremental active transcript branch	Native success/failure hooks	Parent context; native agent ID
Cursor	Prompt and response hooks; duplicate responses suppressed	Native success/failure hooks	Sidekick searches itself; no parent-injection claim
Codex	Native prompt and final-response fields	Structured failure indicators when present; otherwise unknown	Parent context; native agent ID
Kimi	Prompt hooks and completed v2 wire output	Native success/failure hooks	Parent context; without an ID, a stop matches only one unambiguous active run
Antigravity	Incremental completed transcript messages, including later prompts	Native tool errors	Sidekick searches itself; no worktree-isolation claim
Portable v1	Explicit memory skills	No native lifecycle hooks	No native subagent declaration

An uncorrelated subagent completion is kept as its own record; the plugin never guesses which overlapping run completed. Codex's documented hook fields already match the shared input contract, so no speculative field aliases or unsupported failure event are registered.

Offline conformance exercises the adapters and MCP servers with native-shaped payloads and builds each distributable package. It does not establish that every installed editor or Harness version loads the plugin correctly; those checks require smoke tests in the actual hosts.