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.
/plugin marketplace add grpcer/ownmemnpx agentmods add plugins/grpcer/ownmem/marketplacegit clone --depth 1 https://github.com/grpcer/ownmemGrade A, and why
ownmem 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 2d 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
{
"name": "ownmem",
"description": "OwnMem: open-source, Git-native project memory for AI coding agents. This repository doubles as the plugin marketplace.",
"owner": {
"name": "grpcer",
"url": "https://github.com/grpcer"
},
"plugins": [
{
"name": "ownmem",
"source": "./plugins/ownmem",
"description": "Repo-owned project memory for AI coding agents: recall reviewed lessons locally and deterministically, with zero model calls and zero query-time tokens.",
"version": "0.4.0"
}
]
}
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.
- 2d ago First seen · 17 lines scan A 21ca370bda4c
ownmem is a plugin published in the GitHub repository grpcer/ownmem (191 stars, last pushed 6d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
iai-memory
Persistent local memory for your assistant: every turn captured verbatim, relevant memory injected at session start and before each turn, and fifteen memory tools over MCP. Requires the iai-pme package (pip install iai-pme).
iai-pme
The personal memory engine for AI coding assistants — local, encrypted, verbatim.
ultramemory
Plugin marketplace listing 1 plugin: ultramemory-kit.
ultramemory-kit
UltraMemory Agent Kit — recall-first memory (Turbo Token Saver), the grounding/checklist harness, and optional MCP + Playwright setup for Claude Code. Bring your own UltraMemory API key.
krimto
Open-source memory for AI coding agents you own in git — governed by a real user→team→org hierarchy, not a vendor database. Solo to team. Apache-2.0.
krimto
Open-source memory for AI coding agents you own in git — governed by a real user→team→org hierarchy, not a vendor database. Solo to team. Apache-2.0.