Skip to main content
Glama
Sign In
Commons

Commons

by Neoo-Blue
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to Commons

No user-submitted related servers found.

    Related Servers

    • Hivemind

      Lecrupus
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables teams of AI coding agents (Claude Code, Cursor, Codex) to share persistent, time-aware graph memory and coordinate their work via MCP, so agents recall verified fixes at the moment of failure, learn procedures automatically, avoid file conflicts, claim tasks race-free, and hand off facts and decisions between sessions.
      MIT

    • Project Relay

      MuhammadFarhantahirvoltic
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables coding agents in different editors and MCP clients to share messages, project context, notes, task ownership, handoffs, and advisory file claims through a local SQLite-backed coordination server. Supports MCP stdio, MCP Streamable HTTP, a JSON HTTP API, and a local CLI for multi-project agent collaboration.
      MIT

    • memorix

      AVIDS2
      A
      license
      A
      quality
      A
      maintenance
      Cross-agent memory bridge for AI coding assistants. Persistent knowledge graph shared across 10 IDEs (Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro, Antigravity, OpenCode, Trae, Gemini CLI) via MCP. 22 tools including team collaboration, auto-cleanup, mini-skills, session management, and workspace sync. 100% local, zero API keys required.
      9
      1,105 npm
      900
      Apache 2.0
    • Memryzed

      Memryzedofficial

      hamzaarja
      F
      license
      Not graded
      quality
      C
      maintenance
      Local-first cross-agent memory for AI coding agents. Persistent, shared memory over MCP — what you tell one agent can be recalled by another — with all data stored in a single local SQLite file, no cloud and no API keys.
      -
    Deploy Server
    Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    B3.1/5.0

    Scored across 35 tools

    Disambiguation3/5

    Several clusters overlap: msg_send(type=task), summon, submit_task and skill_help all route work to other agents, and two parallel work-tracking systems exist (start_work/finish_work claims vs claim_subtask/heartbeat/complete_subtask). Multiple 'record something' tools (remember, observe_preference, record_decision, add_leftover, board_add) also blur together. Descriptions do help disambiguate, but an agent could plausibly pick the wrong dispatch or tracking tool.

    Naming Consistency3/5

    Some families are consistent (msg_send/msg_recv/msg_get, board/board_add/board_update, start_work/finish_work, claim_subtask/complete_subtask, vault_deposit). But many core tools are bare single words (who, why, turn, remember, search, summon, handoff, resume, infra, pickup, tools, call) with no shared verb_noun convention. Readable overall, but conventions are mixed rather than predictable.

    Tool Count3/5

    35 tools is heavy, and there is clear redundancy (two work-claiming flows, several near-duplicate recording tools), so not every tool obviously earns its place. The underlying domain (messaging, memory, board, credentials, infra, task distribution) is genuinely broad, which partly justifies the size. Borderline-heavy rather than wildly excessive.

    Completeness4/5

    Coverage is strong across the domain: messaging with ack flow, memory store/search/expand/why, board lifecycle, work claims and subtasks with leases, credential vault and use, infra map, handoff/resume, and skills. Minor gaps remain (e.g. no explicit memory delete/forget, and referenced msg_ack is not itself listed). Agents can work around these.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Resources