$ loading_
Give AI coding agents persistent, searchable memory across sessions and tools.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "levh" yet — see the docs or source repo.
Please store these key project conventions in levh memory: use TypeScript strict mode, run tests before commits, and standardize API errors as { code, message }.The AI saves the project conventions into persistent memory for later sessions.
Retrieve previously stored architecture decisions, stack choices, and known constraints for this repository from levh, then summarize them as a short list.
It returns a searchable summary of prior memory to quickly restore context.
Mark “the auth module must remain backward compatible” and “production config changes require backups first” as high-importance items and reinforce their retention in levh.
The AI reinforces retention of critical knowledge so it is less likely to be forgotten later.
Developers can use it to retain project context, conventions, and past decisions when switching across conversations or MCP tools. This helps AI coding agents handle long-running work more consistently.
When a team needs to recall previously recorded implementation constraints, architecture choices, or caveats, its searchable memory can quickly surface them. It is useful for restoring context and avoiding repeated mistakes.
For rules or lessons that must persist over time, this tool uses adaptive decay and reinforcement to help AI retain important information more reliably. It fits critical conventions and high-risk operation reminders.
It is an MCP tool that gives AI coding agents persistent, searchable memory so context can persist across sessions and tools. The description also mentions adaptive decay, reinforcement, spaced repetition, backups, and a knowledge graph.
The known prerequisite is an MCP-compatible client. Other installation details, runtime requirements, or configuration steps are not provided in the given material, so see the source repository.
According to the description, it emphasizes persistence and searchability rather than only keeping context within one chat. It preserves state across sessions and tools and adds decay and reinforcement mechanisms for longer-term knowledge management.
Give AI coding agents persistent cross-project memory and connected context retrieval.
Manage token-efficient memory for AI coding agents with dedup, merge, and decay.
Provide lightweight long-term memory for agents to store and retrieve context.
Provide AI agents with traceable bi-temporal long-term memory in SQLite.
Give AI coding agents persistent local shared memory across agents.
Give AI coding agents offline persistent memory to reduce repeated calls.