$ timeahead.in
/ servers/github/Pensyve
github

Pensyve

Universal memory runtime for AI agents — episodic, semantic, and procedural memory.

36critical
2 credentials detected in repository history via Gitleaks
▣ Score BreakdownMCPScore = Σ(raw × weight)
DimensionRawWeighted
Security
35%
60
21.0
Freshness
25%
30
7.5
Adoption
20%
0
0.0
Quality
10%
20
2.0
Trust
10%
50
5.0
Total
35.5
⚿ Capabilities & Risk Explainer
fs readfs writenetworkexecsecrets
◆ Risk level: high· 8 tools · auth: API key
fs read + fs write + network + exec + secrets active — can execute code, access credentials, and make external network calls.
Tool nameDescriptionDestructive?
pensyve_recallSearch memories using hybrid semantic + BM25 fusion with RRF ranking✓ no
pensyve_rememberStore a fact about a named entity as semantic memory✓ no
pensyve_episode_startBegin tracking an interaction episode with named participants✓ no
pensyve_episode_endClose an episode and extract memories✓ no
pensyve_forgetDelete all memories for an entity✓ no
+3 more tools
pensyve_inspectList all memories stored for an entity✓ no
pensyve_statusNamespace info, memory counts, and connection health✓ no
pensyve_accountPlan, usage, and quota information✓ no
⚙ Install config
Source-only — no published npm / pypi package detected.
Clone and follow the build instructions in the repo: github.com/major7apps/pensyve
📈 Score historylast 18 snapshots
5/25/20266/11/2026 · 18 snapshots
⚙ Maintenance health
55/ 100 · is this project alive?
contributors (1y)2
top contributor share90%
releases (1y)15
last release16d ago
ci⚠ failing
⛁ Raw data
weekly downloads0
github stars0
forks0
open issues0
license✗ missing
readme length0 chars
last updated19d ago
owner of this server? claim your listing to get a verified badgeclaim →
🔔 Score drop alerts
get notified by email when this server's score drops 5+ points
Pensyve — MCP Score: 36/100 | MCPScore | Timeahead