Membrane Agent Skill
by BennettSchwartzA selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
Membrane is an open-source agent skill by BennettSchwartz, written mainly in Go, with 96 GitHub stars and the MIT license. Its code was last updated Sep 5, 2026.
Scan summary: scanned Nov 5, 2026 at commit b3f1f09. No capabilities flagged by our checks. Scan policy
What Membrane can touch
- Our checks did not find this. The tool may still do it.Run shell commandsNot seen in this scan
- Our checks did not find this. The tool may still do it.Run dynamic codeNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or write filesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read environment and secretsNot seen in this scan
- Our checks did not find this. The tool may still do it.Control a web browserNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to databasesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or send messagesNot seen in this scan
- Our checks did not find this. The tool may still do it.Touch money or tradingNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to the internetNot run in this scan
"Not seen" means our checks did not find it, and the tool may still do it. Covers commit b3f1f09, Nov 5, 2026. See the scan policy.
Before you install Membrane
AgenticMart scanned Membrane on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What it can access
- A skill is instructions plus optional scripts. The instructions steer your agent; any scripts run on your machine when the agent uses the skill.
Before you install
- Pin the version you reviewed instead of always installing the latest release.
- Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
- Maintained by BennettSchwartz on GitHub, 96 stars and 12 forks. Popularity is not proof of safety.
- Last code change: Sep 5, 2026.
- Open-source license: MIT.
Membrane is an open-source agent skill by BennettSchwartz, written mainly in Go. A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
At a glance
- Stars
- 96
- Forks
- 12
- Language
- Go
- License
- MIT
- Created
- Jan 2026
- Last update
- Sep 5, 2026
- Type
- Agent Skill
- Price
- Free
Topics
Questions about Membrane
What is Membrane?
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
Who maintains Membrane?
Membrane is maintained by BennettSchwartz on GitHub (BennettSchwartz/membrane). AgenticMart lists it from public repository data.
Is Membrane safe to use?
AgenticMart scanned Membrane on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What license does Membrane use?
It is published under the MIT license.
Membrane alternatives
View more →Similar agent skills in Database Management, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Membrane (this page) BennettSchwartz | 96 | MIT | Sep 5, 2026 | Scanned, no flagged issues |
| Understand Anything Egonex-AI | 90k | MIT | Oct 26, 2026 | Scanned, no flagged issues |
| Scientific Agent Skills K-Dense-AI | 56k | MIT | Oct 26, 2026 | Scanned, no flagged issues |
| Zvec alibaba | 16k | Apache-2.0 | Nov 1, 2026 | Scanned, no flagged issues |
| Claude Obsidian AgriciDaniel | 16k | MIT | Oct 25, 2026 | Scanned, no flagged issues |
| Prompt Master nidhinjs | 15k | MIT | Oct 22, 2026 | Scanned, no flagged issues |