Skip to main content
Glama
IEZhu

Agents-Core

by IEZhu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Agents-Core

  • agent-julia

    elninopl
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first MCP server providing persistent markdown memory with persona engine and fast search, designed to unify AI assistant memory across Claude Code, Cowork, and Dispatch.
    418 npm
    1
    MIT

Related Servers

  • cc-agent

    Gonzih
    A
    license
    A
    quality
    D
    maintenance
    MCP server that spawns autonomous Claude Code agents in GitHub repos, enabling task delegation with persistent state, multi-step workflows, and job monitoring.
    47
    159 npm
    2
    Apache 2.0

  • CHARLIE

    T3CCH
    A
    license
    Not graded
    quality
    B
    maintenance
    Unified knowledge management and agent orchestration MCP server for Claude Code that remembers project patterns, assigns specialist agents, loads relevant knowledge into prompts, and tracks work across sessions to save time and reduce costs.
    1
    GPL 3.0

  • claude-bridge-mcp

    millanrp25-dot
    A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server that lets ChatGPT or any MCP client securely delegate coding tasks to a local Claude Code instance, with git checkpointing, approval gates, and structured results. Supports code review, test running, and rollback via simple tool calls.
    7 npm
    MIT

  • Seamless

    arctop
    A
    license
    A
    quality
    A
    maintenance
    Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).
    30
    6
    MIT
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

B3.4/5.0

Scored across 48 tools

Disambiguation3/5

The set has many distinct domains, but several tools overlap in purpose: get_agent_context, route_and_load, refresh_persona_context, and load_implants all concern persona/agent activation; similarly, get_subagent_context and local_context_create both produce context-like packages. Descriptions are detailed and clarify boundaries, but the sheer number of activation/context/cooperation tools makes misselection plausible.

Naming Consistency4/5

All names use snake_case and generally follow domain-prefixed patterns (local_, artifact_, cooperation_, flow, user_rule), which is predictable. Minor deviations exist in verb placement, such as local_generate versus local_generation_result and noun-first names like local_inference_status, but overall the convention is readable and consistent.

Tool Count2/5

48 tools is far above the reasonable range for agent selection, even accounting for the server's broad platform scope. The surface is split into many subsystems, but the total count creates a high cognitive load and increases the chance of wrong tool selection.

Completeness4/5

The server covers a wide range of lifecycles: local inference, contexts, artifacts and manifests, cooperation, user rules, flows, agents, subagents, history, and repo summaries. Some minor gaps exist, such as no explicit cooperation unregister/release or local-context listing, but most workflows have complete create/read/update/delete coverage.

Maintenance

ActivityMaintained
ResponsivenessResponsive

Resources