A
licenseNot graded
qualityD
maintenanceEnables AI agents to maintain persistent, local memory with retrieval-augmented search, knowledge graphs, and context surfacing, without any cloud dependencies.
103 npm
MIT
slowave
Officialby slowave-ai
Related Servers
Alternatives to slowave
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityAmaintenanceProvides a local-first persistent memory layer that lets AI coding agents store, recall, and semantically search project-specific and cross-project knowledge across sessions, so context, decisions, and guidelines survive between conversations. Runs entirely on the user's machine with SQLite and no API keys, and optionally supports autonomous task-queue execution built on the same memory.-
- FlicenseNot gradedqualityAmaintenanceProvides AI coding agents with a local-first persistent memory layer they can read and write during sessions, storing decisions, preferences, error patterns, and research per project or globally. Enables semantic and keyword search, formatted context recall, and cross-project guideline surfacing without API keys or cloud storage.-
- AlicenseAqualityAmaintenanceGives AI agents persistent, local-first memory using SQLite and on-device embeddings, enabling semantic search and recall across sessions with no cloud calls.89MIT
- FlicenseNot gradedqualityDmaintenanceProvides persistent AI agent memory using a local vector database for long-term semantic storage and short-term session scratchpads. It enables low-latency memory operations including search, storage, and bulk management without external cloud dependencies.-
- FlicenseNot gradedqualityAmaintenanceProvides a local-first, cross-session memory layer that lets AI coding agents store and semantically search per-project decisions, preferences, error patterns, and research alongside global guidelines. Also supports an optional task queue for autonomous execution, all backed by on-disk SQLite with no API keys or external calls.-
TDQS
A4.4/5.0
Scored across 5 tools
Disambiguation4/5
Each of the five tools occupies a distinct phase of an explicit cognitive cycle (open/prime, mid-task lookup, write, assess, close), and the descriptions repeatedly contrast them (e.g. activate 'once at the beginning of every task' vs recall 'deliberate mid-task lookups'). The only real overlap is that activate and recall both perform semantic retrieval, which an agent could conflate without careful reading of the lifecycle guidance.
Naming Consistency5/5
All tools use the identical slowave_ prefix followed by a single snake_case verb (activate, recall, remember, feedback, commit). No mixed conventions, no camelCase, no redundant noun suffixes.
Tool Count5/5
Five tools map cleanly onto one closed lifecycle loop, and each earns its place: retrieval is split into proactive (activate) and reactive (recall) only because the guidance distinguishes them. Nothing feels padded or vestigial.
Completeness4/5
The surface covers open, read, write, assess/correct, and close, with feedback even handling stale/superseded replacement, so core lifecycle is complete. The notable gap is explicit forgetting or deletion of memories, and browsing/listing a scope, which an agent can only approximate via stale feedback.
Maintenance
ActivityActive
ResponsivenessResponsive