Store, search, and log project memories across AI sessions via ZIKRA_URL.
npx skills add https://github.com/getzikra/Zikra --skill zikra-ai-persistent-memory
Please help me install this Agent Skill. Skill: Zikra — AI Persistent Memory Source: https://github.com/getzikra/Zikra/tree/main Command: npx skills add https://github.com/getzikra/Zikra --skill zikra-ai-persistent-memory
Zikra solves the problem of losing important project context between AI sessions and across machines by providing a governed, cross-agent persistent memory store.
Tell your AI agent to store a new decision memory for project yourproject with title and content, then immediately search for related context to continue working.
High-intent search queries and answers about installing and using this skill.
AI persistent memory stores decisions, errors, and prompts in scoped project namespaces so teams can retrieve them later. It applies at session start for retrieval, after key decisions for saving, and on failures for error logging.
The best way to track AI errors and decisions across agents is using a governed persistent memory store with typed categories like decision, conversation, error, schema, and prompt to keep retrieval precise across machines.
You retrieve past prompts at session start by searching scoped project namespaces using a persistent memory tool. This searches past decisions, errors, and context so the right information stays available for continuing work.
A self-hosted MCP is used to enable secure cross-agent persistent memory. It satisfies a YAML-frontmatter-defined skill interface and executes commands securely through configured URL and TOKEN environment variables for project namespaces.
Yes, you can use typed memory categories such as decision, conversation, error, schema, and prompt to keep retrieval precise. This structured approach ensures relevant context stays available for later runs.
You log AI agent failures by recording errors with supporting context on failure events using a persistent memory tool. This captures the error within scoped project namespaces so it can be tracked and found again.
MassimilianoPiliImplement Redis patterns for caching, sessions, and job queues in Docker Compose.
entireioSearch Entire history for checkpoints and agent conversations by topic, repository, branch, author, or time window.
Kirankumar2604Create persistent AI skill units with YAML frontmatter and Markdown documentation.
anajuliabitStore and recall AI agent memories with wallet-based identity and vector search.
