agentpack
Related Servers
Alternatives to agentpack
- AlicenseBqualityAmaintenanceBasic Memory is a knowledge management system that allows you to build a persistent semantic graph from conversations with AI assistants. All knowledge is stored in standard Markdown files on your computer, giving you full control and ownership of your data. Integrates directly with Obsidan.md177,385 PyPI4,075AGPL 3.0
- AlicenseAqualityAmaintenancePersistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB.3088 npm15MIT
- AlicenseBqualityDmaintenanceMCP server for AI-agent handoffs with client-encrypted WorkBaton checkpoints and WorkStash notes.21103 PyPI2Apache 2.0
Related Servers
- FlicenseNot gradedqualityBmaintenanceContainerized MCP server for coding agents with tools for file editing, shell commands, process management, Git, browser automation, and project snapshots.-
- AlicenseNot gradedqualityBmaintenanceEmpower any MCP-compatible AI Agent(MCP Client) with engineering-grade capabilities to understand, modify, run, and deliver real-world code repositories.1,155Apache 2.0
- FlicenseNot gradedqualityCmaintenanceMCP server for the OffByOne website factory, enabling agents to generate, validate, and manage full-stack web projects through safe, deterministic tools.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to generate complete, runnable MCP server projects from natural-language tool descriptions, including schema, implementation, tests, README, and license.MIT
- AlicenseNot gradedqualityDmaintenanceAn agent-ready TypeScript template for building Model Context Protocol (MCP) servers with standardized discovery flows and permission-aware tools. It provides pre-configured core and operable profiles to help developers quickly implement, test, and distribute production-ready MCP services.51 npmMIT
- AlicenseCqualityAmaintenanceProvides a ready-to-use starter kit for building custom MCP servers, enabling developers to scaffold and register tools with type-safe Zod schemas, run over stdio with auto-bootstrapping, and connect to AI clients like Claude Desktop, Google Antigravity, Cursor, and VS Code.31MIT
TDQS
Scored across 25 tools
Each tool targets a distinct action, and descriptions explicitly say when to use and when to avoid each (e.g. task_status vs task_audit, task_park vs task_finalize). The main overlap is load_context vs resume, which produce identical output and differ only in usage context, and bundle_inspect vs bundle_import_plan, which are close but distinguishable.
Most tools follow a clean verb_noun/noun_verb pattern (record_dead_end, attach_evidence, task_start, bundle_import, task_finalize). A few deviate: noun-only names like source_status and release_preflight, plus single-word tools (checkpoint, resume, diff, replay), but overall the set is predictable and readable.
At 25 tools this sits at the heavy end and is borderline for the apparent scope. The domain (task lifecycle, ledger, bundles, context, releases) is broad enough to justify many of them, but the redundant load_context/resume pair and the three-way bundle inspect/plan/import suggest some could be consolidated.
The surface covers the full task lifecycle (start/park/switch/update/verify/finalize/audit/handoff), bundle round-trips (export/import/inspect/plan), ledger recording (decision/dead_end/evidence/source), and context tooling (load_context/resume/checkpoint/diff/replay). Minor gaps exist, such as no way to list or retrieve previously attached evidence, but core workflows are covered.