Mgeeeek
a2516269cc
CLI now consumes the unified mem0_notice surface that the platform side
emits for unclaimed Agent Mode keys. The notice is a directive to the
LLM agent reading the output, with a verbatim sentence to relay to the
human owner. Two presentation paths:
- Human/text output: yellow stderr banner after the primary output,
once per command. Skipped in agent mode (the JSON envelope carries
it instead, so no duplication).
- JSON/agent output (--json/--agent): folded into the envelope as
"mem0_notice" so an agent parsing the output sees it without
inspecting HTTP headers.
CLI changes (Python + Node, kept in lockstep):
- state.{ts,py}: captureNotice / takeNotice helpers — last-write-wins
stash so multi-request commands fire the notice exactly once.
- backend/platform.{ts,py}: _request extracts notice from response
bodies (top-level dict or list[0]) with header fallback, strips
from downstream payload, captures for end-of-command surfacing.
- output.{ts,py}: JSON envelope formatters fold in any pending notice.
- index.ts / app.py: entrypoint surfaces notice on exit when not in
agent mode.
- commands/agent-mode.{ts,py}: init success path prints the platform's
notice verbatim (fallback to dim claim-command line if a stale
backend doesn't return it).
Init-flag handling fix: the Python argv preprocessor was stripping
--agent from sys.argv unconditionally as the global JSON-output alias.
That swallowed `mem0 init --agent` (where --agent is a subcommand flag
for unattended bootstrap). Now preserved when "init" is in argv.
Parity tests: cli/python/tests/test_agent_mode.py and
cli/node/tests/agent-mode.test.ts — 7 tests each, kept in sync.
cli-spec.json updated: init now lists --agent and --source.
Docs:
- README.md: Agent Mode promo at top of Quickstart.
- docs/llms.txt: fast-path block for AI agents reading the docs.
- skills/mem0/SKILL.md, skills/mem0-cli/SKILL.md,
skills/mem0-integrate/SKILL.md, mem0-plugin/skills/mem0/SKILL.md:
autonomous-setup section + fallback hints.
- mem0-plugin/README.md, openclaw/README.md: "Quick path for agents"
blocks above the human Quick Start.
mem0-integrate — Pipeline Skill
Wire Mem0 into an existing repository end-to-end, using a goal-driven, test-first pipeline.
This is a pipeline skill, not a reference skill. Invoke it as
/mem0-integratewhen you want your assistant to do the work of integrating Mem0 into a target repo. For day-to-day SDK coding help, installmem0instead.Part of the Mem0 Skill Graph:
- Reference: mem0 · mem0-cli · mem0-vercel-ai-sdk
- Pipeline: mem0-integrate (this skill) → mem0-test-integration
What This Skill Does
When invoked, your assistant will:
- Detect the target repo's language and stack automatically
- Ask whether to integrate with Mem0 Platform (managed) or Mem0 Open Source (self-hosted)
- Write failing tests first — no implementation until tests exist
- Keep the integration additive and feature-flagged — existing behavior stays byte-for-byte identical when the flag is unset
- Produce a local feature branch (
mem0-integrate/...) and a.mem0-integration/directory of artifacts (goal.md,plan.md,product.json) consumed by the companion verification skill
When to Use
Trigger phrases:
- "Integrate Mem0 into this repo"
- "Add Mem0 to my project"
- "Wire Mem0 into
<repo>" - "How do I add memory to an existing project?"
Do not use this skill for general SDK usage (install mem0), terminal workflows (install mem0-cli), or Vercel AI SDK integration (install mem0-vercel-ai-sdk).
Installation
CLI (Claude Code, Codex, OpenCode, OpenClaw, or any tool that supports skills)
npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate
For verification on the same branch, also install the companion skill:
npx skills add https://github.com/mem0ai/mem0 --skill mem0-test-integration
Claude.ai
- Download this
skills/mem0-integratefolder as a ZIP - Go to Settings > Capabilities > Skills
- Click Upload skill and select the ZIP
Claude API (Skills API)
curl -X POST https://api.anthropic.com/v1/skills \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{"name": "mem0-integrate", "source": "https://github.com/mem0ai/mem0/tree/main/skills/mem0-integrate"}'
Prerequisites
- A Mem0 Platform API key (get one) or a working OSS setup (LLM + vector store)
- Python 3.10+ or Node.js 18+ in the target repo
- A clean working tree on the target repo's default branch
Workflow
/mem0-integrate → creates mem0-integrate/<slug> branch,
writes .mem0-integration/ artifacts,
implements against failing tests
/mem0-test-integration → runs the repo's native test suite,
executes a real end-to-end smoke flow,
produces a scorecard
The two skills are loosely coupled — they share the same workspace and branch via .mem0-integration/, but the verifier never modifies source.
Links
License
Apache-2.0