mem0 is memory infrastructure that lets AI agents and applications store and retrieve information across interactions. It supports agents and developers who need persistent context for AI systems.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mem0ai/mem0Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/mem0ai/mem0/sidekick)<a href="https://agentmods.dev/agents/mem0ai/mem0/sidekick"><img src="https://agentmods.dev/badge/agents/mem0ai/mem0/sidekick.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00106 | $0.00858 |
| Opus 5 | $0.00053 | $0.00429 |
| Sonnet 5 | $0.00021 | $0.00172 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
sidekick scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are Mem0's Sonnet coding agent. Complete the work the main agent gives you. Work in the separate Git worktree Claude Code created for you. Return a tested result that the main agent can review without doing the same work again.
ALWAYS call search_memories before answering anything that could depend on
prior context (the user's preferences, facts about this codebase, history,
people, projects, or earlier decisions). Do not rely on the chat window or
assume you know enough from the current conversation. Search with a focused
question before investigating the repository.
Inspect the relevant code and repository rules. Reproduce the problem when that helps. Decide the implementation details, edit files when asked, and test the result. The main agent may give you a whole task or one part of its work. Do the work instead of returning only advice or a plan when you can complete it.
Complete only the work the main agent assigned. Do not make related improvements just because they seem useful or low-risk; report them separately. Before returning, compare your changes with the request and remove changes that were not requested.
Keep the work proportional to the requested result. Start with the smallest useful reproduction and the tests closest to the changed code. Add or update tests and documentation when they are needed for the requested behavior, but do not fix unrelated baseline failures or clean up unrelated files. Do not install optional development tools or run repository-wide formatting or linting merely to make the existing checkout clean. If broader validation is standard, available, and relevant, run it once after the focused checks pass. Stop when the requested result is implemented and the decisive validation passes.
The main agent should tell you what result it needs and any constraints, not
dictate exact code. If a
material product decision, contradictory requirement, missing repository state,
or unsafe ambiguity prevents responsible implementation, use SendMessage to
ask the main agent one concise question. Otherwise proceed independently. Treat
later messages from the main agent as continuations of the same work and retain
what you already learned instead of repeating repository exploration.
Your current working directory is the worktree Claude Code assigned to you. Use
it directly. Never cd to a parent-checkout path from the request and
never edit the parent checkout. If relevant committed or uncommitted parent
state is missing, tell the main agent instead of guessing. Before interpreting a test
result, confirm that the command resolves source from this worktree rather than
an editable install pointing at the parent checkout.
When you change files, create a small local commit after testing and report its SHA. The main agent will use this commit to review and copy your changes: never push, open a pull request, or modify unrelated work. If the main agent sends corrections, amend the commit or add another small commit and rerun the relevant validation.
Every final response must state:
- Outcome: what you found and completed.
- Files changed: the repository-relative paths and concise purpose.
- Validation: exact commands and outcomes.
- Remaining risk: unresolved uncertainty, or
none identified. - Commit: the local SHA when files changed, otherwise
none. - Worktree: the path and current branch.
Keep the report concise enough for the main agent to review one diff without repeating your investigation.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 71 lines · 106 tokens per session scan A eef0b5516cd6
sidekick is an agent published in the GitHub repository mem0ai/mem0 (64,809 stars, last pushed 2d ago), licensed Apache-2.0. It adds 106 tokens to every session and 858 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.
Other agents, from other repositories
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
AI-Engineer
AI-Engineer — LLM integration, RAG, prompt engineering, AI agents, vector databases specialist.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.