mem0
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Runs with mockssource: GitHubhomepagePythonApache-2.0commit 8d6c00196657
Python, Apache-2.0 licensed. The project labels itself: agentic memory, agentic memory system, agents, ai, ai agents, chatgpt, genai and llm.
mem0 runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Mem0 SDK 2.2.0 installs cleanly in a Python 3.12 venv with all optional dependencies; 1845/1922 pytest test cases pass (77 skipped due to missing external services), 0 failures.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- OPENROUTER_API_KEY env var from Codex CLI pollutes OpenAI tests, causing 7 test failures8 minutes
- test_main.py OOM-killed (exit 137) with MEM0_TELEMETRY=True due to torch import from telemetry chain5 minutes
- httpx proxy URL pattern validation rejects bare scheme keys2 minutes
- test_notices.py and test_oss_to_platform_migrate.py need MEM0_TELEMETRY=True but default is False1 minute
- Install time
- 12 minutes
- Cold machine to finish
- 49 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pytest tests/ --ignore=tests/test_main.py (MEM0_TELEMETRY=True): 1801 passed, 77 skipped, 0 failed; pytest tests/test_main.py (MEM0_TELEMETRY=False): 44 passed, 0 failed
- Model tokens used
- 1,148,324
- Exact commit tested
- 8d6c00196657
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
| Error | Root cause | Fix | |---|---|---| | `test_openai.py` failures (7 tests) | `OPENROUTER_API_KEY` set in Argusic Agent CLI agent env cau… | `test_main.py` OOM-killed (signal 9) | Running with `MEM0_TELEMETRY=True` triggers PostHog + `_ge… | Proxy test failures | `build_http_client()` in `mem0/utils/http.py` passes dict keys as httpx URL… | `test_async_notice_wrapper_uses_shared_helper` failure | `display_first_run_notice_async` returns… | `test_oss_to_platform_migrate.py` failures (7 tests) | Assertions on `updated["telemetry"]["alias… | `test_memory_initialization_opensearch_aws_auth` failure | `mock_vector_factory.call_count >= 2` … **What was verified:** - Core SDK imports (`Memory`, `AsyncMemory`, `MemoryClient`, `AsyncMemoryClient`, `MemoryConfig`) - All 1845 tests pass across configs, embeddings, LLMs, memory, rerankers, vector stores, telemetry… - The SDK installs, builds, and runs correctly in a container environment without real API credenti…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 12 minutes.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.23 |
Topics (from GitHub)
agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mem0)Questions
- Does mem0 run?
- mem0 runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test mem0?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8d6c00196657. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mem0?
- The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mem0 take to install?
- 12 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does mem0 need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mem0?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for mem0?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.