agentic-recall
Related Servers
Alternatives to agentic-recall
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceEnables Claude to retrieve relevant memories from a folder of markdown files using hybrid search (BM25F, dense embeddings, phrase proximity) and to explicitly report when no strong match exists instead of guessing.16 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides local-first, cross-session memory for Claude Code, enabling semantic search across past sessions to retrieve procedures, decisions, or answers without exposing secrets.Apache 2.0
- AlicenseAqualityCmaintenanceEnables Claude to query user-curated, dated memory entries stored locally, giving users direct control over what the AI remembers about them.487 PyPI1MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude Code to search and retrieve from a local knowledge base of markdown notes using hybrid semantic+keyword search, keeping data entirely offline.6 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code to automatically recall and write shared long-term memories stored as plain Markdown, combining BM25, vector, and link-graph hybrid search so relevant notes are injected on every prompt. Memories persist across sessions, projects, and machines, with status tracking for pending and resolved items plus optional end-of-session curation.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude Code to use local markdown notes as persistent, searchable memory with hybrid recall, episodic memory, note-graph traversal, design memory, and optional cloud sync.136 npmMIT
TDQS
Scored across 2 tools
The two tools have mutually exclusive purposes: memory is read-only retrieval with many actions, while memory_write is exclusively for writes (import, capture, index, tier changes). There is no overlap in functionality, so an agent can unambiguously choose based on whether it needs to read or write.
Both tool names share the 'memory' prefix, with '_write' clearly marking the write operation. This is a simple, predictable convention that mirrors the underlying domain, and there are no mixed naming styles or vague verbs.
With only two tools, the surface feels thin at first glance, but the memory tool consolidates a large set of read actions (search, latest, sessions, thread, verify, get, neighbors, index_status, probe_status) into one interface. This is a borderline case — the count is low, but the scope is narrow enough that a read/write pair is reasonable.
The tool set covers the full memory lifecycle: comprehensive reads (search, get, thread, verify, sessions, neighbors, freshness), writes (import, capture, index, demote/promote), and administrative operations (index_status, probe_status). The deliberate absence of deletion is clearly documented and does not create a dead end, as content is designed to persist.