Skills
smart-memory
by BluePointDigital
A local, persistent cognitive OS for AI agents.
Our verdict
We have not reviewed smart-memory yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About smart-memory
A local, persistent cognitive OS for AI agents. It provides continuous background consolidation, curiosity triggers, emotional weighting, and lightning-fast Nomic vector retrieval via a persistent FastAPI brain.
Best for
Developers building Python-based AI agents that need persistent, context-aware memory.
Use cases
- Give agents long-term memory across sessions
- Enable curiosity-driven exploration of stored data
- Retrieve relevant memories with emotional context
Notes
25 stars on GitHub. Last updated 2026-03-06.
Pros
- Local and persistent, keeping data on your infrastructure
- Fast retrieval using Nomic vectors
- Background consolidation reduces manual memory management
Cons
- Requires running a FastAPI service, adding operational overhead
- Emotional weighting may be overkill for simple use cases
- Small community (25 stars) means limited support
Key facts
What we have checked
- Days since the last commit
- 252
- GitHub forks
- 2
- GitHub stars
- 25
- Open issues
- 3
- Releases in the last 90 days
- 0
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How smart-memory is growing
25 to 25
Health and security
Is smart-memory looked after, and what do its setup files show
Health score
17 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 10.1 of 30 | Last push 252 days ago |
| Releases | 0 of 15 | 0 releases in 90 days |
| Issue replies | Not counted | The latest check has no issue response reading (fewer than 3 measured issues, or issues switched off) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | Not counted | MCP servers only |
Security check static checks
34 out of 100
- Critical PyTorch: `torch.load` with `weights_only=True` leads to remote code execution (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium PyTorch Improper Resource Shutdown or Release vulnerability (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium PyTorch is Vulnerable to Memory Consumption through pad_packed_sequence Function (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium PyTorch is vulnerable to memory corruption through its unpack_sequence function (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Medium Advisory (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Low PyTorch susceptible to local Denial of Service (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Low PyTorch Tuple Handler is Vulnerable to Memory Corruption through Manipulation of None Argument (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Low PyTorch is vulnerable to memory corruption through its torch.lstm_cell function (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Low PyTorch is vulnerable to memory corruption through its torch.jit.script function (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Low PyTorch: Manipulation of the argument scale/zero_point leads to improper initialization via Quantized Sigmoid Module (affects torch 2.5.1+cpu, pinned in requirements-cpu.txt).
- Low Downloads code and runs it straight away (a well-known installer), host raw.githubusercontent.com: install.sh, line 3.
- Low Sends data to a host outside the well-known APIs (to an address set at run time): skills/smart-memory-openclaw/SKILL.md, memory_adapter.py, smem-hook.sh, line 52, 5 places in all.
- Note 46 files were not read (over 512 KB, or past the 60 file cap): retrieval/backend.py, retrieval/entity_detector.py, retrieval/reranker.py and more.
- Note 8 of 11 packages are not pinned to one version, so only the malicious packages list was checked for them, not version advisories.
Alternatives
Alternatives to smart-memory
| Record | Type | How we know | Checked |
|---|---|---|---|
| everme-memoryThis is an alternative to it | Skill | Matched from the listing text | |
| Honcho Memory for HermesThis is an alternative to it | Skill | Matched from the listing text | |
| streamient-memoryThis is an alternative to it | Skill | Matched from the listing text |
Compare
Compare smart-memory side by side
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Security finding
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
everme-memory
EverMind-AI
Open-source CLI and Agent plugin suite for EverMe — cross-device, cross-Agent personal memory for AI Agents.
Honcho Memory for Hermes
Nous Research
Set up and troubleshoot Honcho cross-session memory for Hermes Agent, cloud or self-hosted.
streamient-memory
streamient
Open source memory infrastructure for AI and humans. Turn scattered knowledge into AI-ready context across Claude, Cursor, ChatGPT, and any MCP client.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
claude-mem-install
thedotmack
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessi
memory-notes
basicmachines-co
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
memory-quest
basicmachines-co
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
mem-search
thedotmack
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessi
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.