aether-cache
Related Servers
Alternatives to aether-cache
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceProvides a local long-term memory layer for AI coding tools like Cursor and Claude Code, enabling cross-session, cross-tool sharing of project facts, user preferences, decisions, and workflows.12 npm2MIT
- AlicenseAqualityAmaintenanceOne local memory every coding agent on your machine shares — Claude Code, Cursor, Claude Desktop, OpenCode. Answers from past sessions, commits, CLAUDE.md/AGENTS.md and ADRs with the exact source, and withholds work another agent has claimed so two agents don't rewrite the same thing.35,576 PyPI1MIT
- AlicenseBqualityAmaintenancePersistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.79269 PyPI73MIT
- FlicenseNot gradedqualityBmaintenanceLocal-first memory for AI coding agents. Indexes your Claude Code, Codex, Cursor, Cline and Gemini CLI history by repo/branch/worktree and hands a context capsule (decisions, touched files, next steps) to the next agent over MCP.-
- AlicenseNot gradedqualityBmaintenancePortable AI memory that roams with you across models and harnesses — one shared memory for Claude Code, Codex, Cursor, Gemini CLI and more, stored as plain markdown files you own. Per-project spaces plus a shared layer, vault-wide search; runs locally over stdio/HTTP or hosted with OAuth 2.1 backed by your own GitHub repo.55 npmMIT
- AlicenseAqualityDmaintenanceHybrid semantic + keyword memory across all your projects. Works with Cursor, Claude Code, and your team.1124 PyPI1MIT
TDQS
Scored across 10 tools
Most tools have distinct purposes (create, read, inspect, sync, conflict management), but there is a cluster of retirement-oriented tools (mark_outdated, replace_memory, check_stale, resolve_conflict) that could be confused at a glance. Detailed descriptions mitigate the overlap, so an agent can usually select correctly.
The set is predominantly verb_noun in snake_case (explain_memory, mark_outdated, replace_memory, check_stale, confirm_memory, sync_to_files, list_conflicts, resolve_conflict), but two foundational tools (remember, recall) are bare verbs. This is a minor deviation that remains readable and largely predictable.
With 10 tools, the set is well-scoped for project memory management. Each tool serves a clear role across creation, retrieval, lifecycle, and conflict resolution, and no tool feels redundant or missing.
The lifecycle is well covered: create, search, inspect provenance, retire, replace, confirm, sync, and resolve conflicts. However, there is no explicit hard-delete or purge operation, and no direct way to list all memories without a semantic search, which are minor gaps for the domain.