Skip to main content
Glama
Sign In
MileStack

MileStack

by SuperYang006
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to MileStack

No user-submitted related servers found.

    Related Servers

    • vibecheck

      mgd34msu
      F
      license
      A
      quality
      A
      maintenance
      Enables coding agents to track and coordinate project work through a shared SQLite ledger, including task plans, session ancestry, claims, work locations, blockers, and commits via MCP tools.
      9
      -

    • Commons

      Neoo-Blue
      A
      license
      B
      quality
      A
      maintenance
      Lets multiple AI agents and parallel coding sessions share one memory and task ledger, so they can claim work instead of duplicating it, resume each other's handoffs and reasoning, and use credentials without ever seeing the keys. Connects assistants such as Claude Code, Codex, Cursor, Gemini, ChatGPT and custom agents over MCP, backed by a single local SQLite file or a self-hosted Postgres hub.
      35
      MIT
    • agentbus

      agentbusofficial

      RetentionSoftware
      A
      license
      Not graded
      quality
      C
      maintenance
      A local MCP server that lets parallel coding sessions in one repository coordinate, by registering agents with roles and statuses, delivering messages directly into their context, tracking tasks with dependencies, and claiming file paths to detect conflicts. It runs as a single loopback-only Python process backed by SQLite, with no accounts or external services.
      MIT

    • Synapse MCP

      holaluiz
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables multiple AI coding agents to work concurrently on the same repository by coordinating task ownership, file locks, architectural decisions, investigation gaps, handoffs, and audit activity through a local SQLite-backed MCP interface.
      12 npm
      MIT
    • AgentTasker

      AgentTaskerofficial

      BadbotAI
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to create, query, update, claim, hand off, and complete tasks on a local SQLite-backed, project-namespaced kanban board through stdio MCP tools, including filtering for ready/blocked/stale work and exchanging task attachments. It also lets agents list projects and manage statuses, ownership, and evidence without any server or accounts.
      MIT
    Deploy Server
    Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

    TDQS

    A3.7/5.0

    Scored across 15 tools

    Disambiguation3/5

    Most tools map to a distinct lifecycle step, but the review-conclusion trio (approve_review, request_changes, complete_review) is genuinely hard to separate: approve_review and complete_review both describe recording a pass with structured findings, closures, and evidence. get_project_status vs list_tasks vs get_task are saved by descriptions that explicitly say when to use which, but the agent still must reason about overlapping read views.

    Naming Consistency5/5

    Uniform snake_case verb_noun pattern throughout (get_, list_, create_, edit_, start_, update_, submit_, approve_, request_, check_), including the predictable singular/plural pair create_task/create_tasks. No casing or style deviations.

    Tool Count4/5

    15 tools sits at the top of the well-scoped range, but each covers a real lifecycle stage (intake, execution, submission, review, integration) rather than a redundant variant. A couple of review tools could plausibly be folded together to tighten the set.

    Completeness3/5

    Core lifecycle is well covered (create single/batch, read, claim, progress, submit, review, approve/changes, integration retry, instructions), but notable gaps remain: no delete/cancel/abandon operation, no way to list pending reviews or fetch a review without a developer-supplied task ID, and task definitions are only editable while in inbox.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Resources