A
licenseA
qualityC
maintenanceSmart memory for AI agents. Solves the Karpathy problem: memories decay, topics are frequency-weighted, one-time questions don't become obsessions. 7 tools. Zero deps.
4
13 npm
2
MIT
agentic-task-system
Related Servers
Alternatives to agentic-task-system
Related Servers
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent, local-first memory so project decisions, preferences, and cross-project guidelines survive across sessions and can be retrieved by semantic search. Optionally also exposes a task queue for autonomous execution that draws on the same stored context.-
- 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 gradedqualityAmaintenanceEnables AI coding agents to store, search, and recall persistent project-specific and cross-project context — decisions, preferences, error patterns, and guidelines — from a local-first SQLite memory store with semantic search, so knowledge survives across sessions. An optional companion task server lets agents queue and autonomously execute work using that same memory.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to read and write persistent project-scoped and cross-project memory during sessions, using local semantic search to surface relevant decisions, preferences, error patterns, and guidelines across sessions. It also optionally exposes an autonomous task queue that draws on that same stored context.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to save and recall persistent project and cross-project context across sessions through semantic search over a local SQLite store, with no external API keys required. Optionally exposes a task queue so agents can pick up, execute, and commit queued work autonomously.-
- FlicenseNot gradedqualityAmaintenanceProvides a local-first persistent memory layer that AI coding agents can read and write during sessions, enabling semantic search and recall of project decisions, preferences, error patterns, research, and cross-project guidelines stored in local SQLite. It also exposes an optional task queue and orchestration tools for delegating autonomous coding work that reuses the same stored context.-
TDQS
A3.5/5.0
Scored across 32 tools
Disambiguation4/5
Most tools are clearly scoped to a distinct operation (CRUD, lifecycle, security, linking, events), and ambiguous pairs like find vs. similar are explicitly disambiguated. Minor overlap remains between add_task_link, add_task_reference, and relate_task, as well as task_graph vs. context_for_task, but the descriptions give enough guidance to avoid serious misselection.
Naming Consistency4/5
The naming convention is predominantly snake_case verb_noun with predictable set_/get_/list_/create_/update_/remove_ prefixes. A few tools break the pattern—find, similar, url_for, task_graph, context_for_task—but these are readable and not chaotic.
Tool Count2/5
32 tools is well past the 25+ threshold and creates a heavy surface for an agent to choose from. Many tools represent distinct subdomains, but the overall count feels bloated; consolidating related operations or naming grouped tool families would make the set more usable.
Completeness4/5
The server covers task CRUD, lifecycle, hierarchy, intent, security, relationships, references, context building, search, deduplication, deep links, action ledger, undo, and event observation—an unusually broad and complete surface. Minor gaps exist, such as no explicit delete_task operation and no straightforward list_all_tasks beyond search or project listing, but agents can work around these with existing tools.
Maintenance
ActivityActive
ResponsivenessUnresponsive