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 Skills for AI Coding Assistants
Mem0 ships structured skill definitions for Claude Code, Codex, Cursor, OpenCode, OpenClaw, and any assistant that supports the skills standard. Skills teach the assistant how to work with Mem0 — either by loading SDK knowledge into context, or by executing an end-to-end workflow on demand.
Two Categories
Reference skills — always on
Installed once, loaded into context so the assistant writes correct Mem0 code. Use these for day-to-day development.
| Skill | Surface | Install |
|---|---|---|
mem0 |
Python + TypeScript SDKs (Platform + OSS), framework integrations | npx skills add https://github.com/mem0ai/mem0 --skill mem0 |
mem0-cli |
Terminal workflows (mem0 CLI, both Node and Python) |
npx skills add https://github.com/mem0ai/mem0 --skill mem0-cli |
mem0-vercel-ai-sdk |
@mem0/vercel-ai-provider and createMem0 |
npx skills add https://github.com/mem0ai/mem0 --skill mem0-vercel-ai-sdk |
Pipeline skills — run on demand
Invoked as a slash command to execute a specific end-to-end workflow. These do real work: they create branches, write tests, run code.
| Skill | Trigger | Install |
|---|---|---|
mem0-integrate |
/mem0-integrate — wire Mem0 into an existing repo via TDD |
npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate |
mem0-test-integration |
/mem0-test-integration — verify what /mem0-integrate produced |
npx skills add https://github.com/mem0ai/mem0 --skill mem0-test-integration |
The two pipeline skills are designed to run in sequence on the same workspace:
/mem0-integrate → mem0-integrate/<slug> branch + .mem0-integration/ artifacts
/mem0-test-integration → scorecard (compile + runtime verification, real API smoke test)
Choosing a Skill
- Writing Mem0 code in a new or existing project? →
mem0 - Using the terminal CLI? →
mem0-cli - Building with
@ai-sdk/*? →mem0-vercel-ai-sdk - Want the assistant to wire Mem0 into an existing repo for you? →
mem0-integrate, thenmem0-test-integration
Links
- Vibecoding with Mem0 — canonical landing page
- Claude Code integration
- Mem0 Platform Dashboard
- Mem0 Documentation
License
Apache-2.0