kartik-mem0
c8b93de8e9
README first fold: - banner 800px -> 520px - badges condensed from two paragraphs into one row (Trendshift kept, inline) - lead with Introduction instead of benchmarks - new How it works section explaining the add/search loop - benchmarks moved below the intro and retitled from the date-stamped New Memory Algorithm (April 2026) - dropped Research Highlights, which restated the benchmark table verbatim Benchmarks: the README was already correct at 92.5 / 94.4, matching mem0.ai/research and docs/core-concepts/memory-evaluation.mdx. The stale copies were in the migration guides, which quote the numbers as a live reason to upgrade. Updated both to 92.5 / 94.4 (+21 / +27). docs/changelog/highlights.mdx keeps 91.6 / 93.4 inside its dated 2026-04-14 entry, which records what was announced at the time. One-liner: standardized on 'the memory layer for AI agents', already the canonical form in cli-spec.json, cli/python/pyproject.toml and the CLI specification. Swept the remaining variants.
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 |
mem0-oss-to-platform |
/mem0-oss-to-platform — migrate a project from Mem0 OSS to the hosted Platform SDK |
npx skills add https://github.com/mem0ai/mem0 --skill mem0-oss-to-platform |
The mem0-integrate and mem0-test-integration 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 - Already using Mem0 OSS and want to move to the hosted Platform? →
mem0-oss-to-platform
Links
- Vibecoding with Mem0 — canonical landing page
- Claude Code integration
- Mem0 Platform Dashboard
- Mem0 Documentation
License
Apache-2.0