cogvault
Related Servers
Alternatives to cogvault
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceProvides coding agents with persistent local memory by exposing tools to save, search, and retrieve decisions, bugs, and context as Markdown with hybrid keyword and semantic search.4MIT
- AlicenseNot gradedqualityAmaintenanceLocal-first memory for AI agents: one store shared by Claude Code, Codex CLI, Cursor, Pi, Hermes, OpenClaw, and any MCP client. Plain markdown with YAML frontmatter on your disk, hybrid BM25 + vector recall with per-result provenance (Recall X-ray), a correction contract, and the MemCorrect benchmark.229MIT
- AlicenseNot gradedqualityAmaintenanceMarkdown-first long-term memory for AI coding agents, enabling hybrid search over local files via MCP tools.18Apache 2.0
- AlicenseNot gradedqualityAmaintenanceLocal-first, file-based memory layer for AI agents — one shared Markdown vault across Claude, Codex, Gemini, Cursor and any MCP client. Provides read/write memory tools with an audit trail, per-agent trust levels, and Git sync; no cloud and no lock-in.2MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to capture, structure, remember, and retrieve source-backed memory as local Markdown files, with reviewable writes and no cloud dependency.218MIT
- AlicenseNot gradedqualityBmaintenancePersistent cognitive memory for AI agents. Sub-millisecond recall, fully offline, encrypted. 8 tools: recall, recall_structured, store, store_code, store_decision, search, insights, consolidate.1,162 PyPI85MIT
TDQS
Scored across 2 tools
The two tools are perfectly complementary: cogvault_recall is read/search and cogvault_record is write/save. There is no overlap, and the descriptions make the read-before-write workflow explicit, so an agent can never confuse them.
Both names follow the same predictable pattern of a namespace prefix plus a clear verb (cogvault_recall, cogvault_record). This is a consistent, readable convention with no deviations.
Two tools is the bare minimum for a persistent memory store covering store and retrieve. It is borderline thin; a memory service realistically needs at least update/delete/forget to feel well-scoped.
The core save-and-search lifecycle is covered, but there is no way to update, correct, or delete a memory card once recorded, and no listing or browsing operation. These are notable gaps that could force agents to rely on superseding stale cards.