Skip to main content
Glama

Sistema de Agentes

Un orquestador multi-agente duradero con:

  • grafos de ejecución explícitos y puntos de control/reanudación

  • delegación paralela controlada por el orquestador

  • ejecución de enjambre de investigación acotada

  • bucles de codificación, revisión, reparación, CI y aprobación

  • memoria de proyecto en almacenes de respaldo expuestos a través de recursos y herramientas MCP

  • un índice vectorial de SQLite real para la recuperación de memoria

  • un backend de investigación externo conectable con soporte para Tavily

Alcance

Esta implementación apunta a la línea base de la especificación MCP 2025-11-25 con el SDK oficial de Python para MCP y un servidor FastMCP para la superficie de memoria. Para el desarrollo local, se ejecuta sobre stdio. Para la implementación remota, consulte docs/remote_auth.md.

Related MCP server: ellmos-homebase-mcp

Diseño

  • app/runtime: estado de ejecución, programador, bucle del orquestador, puntos de control

  • app/planner: ayudantes de planificación y revisión de grafos

  • app/agents: ejecutores de nodos para investigación, código, revisión, reparación, CI, síntesis, aprobación

  • app/memory: memoria respaldada por SQLite, recuperación e índice de artefactos

  • app/mcp_server: recursos, herramientas, prompts y punto de entrada del servidor FastMCP

  • tests: cobertura de aceptación y unitaria

Uso local

uv sync --group dev
uv run pytest
uv run agent-system-mcp

Backends de recuperación e investigación

  • Las entradas de memoria se indexan en una tabla vectorial de SQLite local utilizando sqlite-vec.

  • El proveedor de incrustaciones (embedding) predeterminado es auto: prefiere un modelo real de sentence-transformers y recurre al proveedor de hash determinista solo si el modelo no se puede cargar.

  • La investigación utiliza un backend de corpus en memoria cuando un nodo proporciona inputs.corpus.

  • Si se establece TAVILY_API_KEY, los nodos de investigación sin corpus pueden usar el backend de Tavily para investigación web externa.

  • Si no hay corpus ni clave de Tavily disponibles, la investigación devuelve hallazgos vacíos acotados en lugar de inventar fuentes.

Configuración de incrustaciones (embedding)

  • AGENT_SYSTEM_EMBEDDING_PROVIDER=auto|sentence-transformers|hash

  • AGENT_SYSTEM_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2

  • AGENT_SYSTEM_EMBEDDING_CACHE_DIR=/path/to/cache

  • AGENT_SYSTEM_EMBEDDING_LOCAL_ONLY=true|false

Ejemplo:

AGENT_SYSTEM_EMBEDDING_PROVIDER=sentence-transformers uv run agent-system create-run "improve scheduler"

Transporte local

El desarrollo utiliza el transporte stdio de MCP.

Implementación remota

La implementación remota es intencionalmente solo para documentación en la v1. El servidor documenta una ruta de consentimiento compatible con OAuth 2.1 y mantiene stdio local como el modo de desarrollo predeterminado.

Documentación completa

Available Tools

10 tools
checkpoint_runB
Idempotent

Apply a small state patch and create an explicit checkpoint.

Inputs: run_id (required), state_patch_json (required). Returns: object

create_runA

Create a new orchestrator run from a high-level goal and optional JSON spec.

Inputs: goal (required), spec_json. Returns: object

get_file_contextB
Read-onlyIdempotent

Read file context from the orchestrator workspace.

Inputs: paths (required), include_neighbors. Returns: object

plan_goalB
Read-onlyIdempotent

Generate a large-app execution blueprint from a high-level goal and optional JSON spec.

Inputs: goal (required), spec_json. Returns: object

record_decisionC
Idempotent

Record a high-value architectural or implementation decision.

Inputs: title (required), run_id (required), node_id (required), rationale (required), +2 more. Returns: object

record_failure_modeA
Idempotent

Record a reusable failure pattern or bug signature.

Inputs: run_id (required), node_id (required), summary (required), signature (required), +1 more. Returns: object

resume_runA
Idempotent

Resume an orchestrator run until completion, pause, or failure.

Inputs: run_id (required). Returns: object

search_project_memoryA
Read-onlyIdempotent

Search project memory by query string and optional type filters.

Inputs: query (required), kind, limit, status. Returns: result

write_project_memoryC
Idempotent

Write a durable memory entry with provenance to the backing store.

Inputs: key (required), kind (required), run_id (required), node_id (required), +5 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 10 tools

    Disambiguation3/5

    Most tools target distinct actions or resources, but plan_goal and create_run both take a high-level goal and optional JSON spec, making their boundaries unclear. Similarly, search_project_memory and list_related_artifacts both retrieve stored information in overlapping ways. Descriptions help clarify intent, but some pairs could still lead to misselection.

    Naming Consistency5/5

    All tools follow a consistent verb_noun snake_case pattern, such as resume_run, write_project_memory, record_decision, and create_run. The naming is uniform and predictable across the entire toolset.

    Tool Count5/5

    Ten tools is a well-scoped count for an orchestrator and memory management server. Each tool covers a meaningful operation without the set feeling bloated or overly sparse.

    Completeness4/5

    The core lifecycle is covered: creating and resuming runs, checkpointing, planning, memory read/write, and recording decisions/failures. Minor gaps exist, such as no explicit run status/query tool or delete operation for memory entries, but agents can generally work within the provided surface.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Shared memory and orchestration for coding agents, enabling persistent knowledge, multi-agent coordination, and a canonical workflow across MCP-compatible AI clients.
      83
      -
    • A
      license
      C
      quality
      B
      maintenance
      Enables local-first LLM orchestration with persistent memory, knowledge management, routing, swarm patterns, API probing, tests, automation planning, and plugin discovery via a stdio MCP server, using SQLite for offline storage.
      51
      173 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A production-grade multi-agent workflow orchestrator built on the Model Context Protocol, featuring planner/executor/critic agents, durable run state, and replayable traces.
      15
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables autonomous multi-agent orchestration using directed acyclic graph workflows to interact with external developer infrastructure such as Git, Postgres, and Docker through safety-gated MCP servers.
      Apache 2.0