Universal memory runtime for AI agents
This repository also configures its own agents. See what pensyve tells them →
Skill Claude CodeCodex
Session-start context loading -- loads historical decisions, issues, and patterns from Pensyve to provide cross-session continuity. Use at session start or when switching context.
Skill Claude CodeCodex
Delete all Pensyve memories for one entity only after explicit destructive-action confirmation.
Skill Claude CodeCodex
View Pensyve memories for an entity, grouped by type, with optional type and limit filters.
Skill Claude CodeCodex
Pre-refactor context briefing -- loads relevant prior decisions, failures, and pitfalls from Pensyve memory before refactoring a module. Use before any refactor to avoid repeating past mistakes.
Skill Claude CodeCodex
Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.
Skill Claude CodeCodex
Search persistent Pensyve memory by semantic similarity with optional entity and result-limit filters.
Skill Claude CodeCodex
Store a fact, decision, or pattern in persistent Pensyve memory after checking for duplicates and secrets.
Skill Claude CodeCodex
End-of-session memory capture -- classifies session signals using a tiered taxonomy and stores confirmed items via Pensyve. Use when ending a work session or when the user wants to capture what was learned.
Skill Claude CodeCodex
Use when the user types @pensyve, asks for an @-mention workflow, wants mention-style Pensyve memory access in Codex, or asks whether Pensyve supports Codex mentions.
Skill Codex
Use when the user explicitly invokes Pensyve, asks what the agent remembers, wants Codex to recall or store project memory, requests memory health review, or wants memory grounded work.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: