Skip to main content
Glama
adyoi

Cortex Intelligent

by adyoi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to Cortex Intelligent

No user-submitted related servers found.

    Related Servers

    • genpark-personal-agent-dual-cognition-orchestrator-skill by alphaparkinc

      genpark-personal-agent-dualofficial

      alphaparkinc
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables personal AI agents to perceive ambient context, retain episodic memory with decay, act proactively, and route routine decisions through fast System-1 reflexes while escalating ambiguous multi-hop plans to frontier LLMs. Includes reversible execution checkpoints, token budgets, and local-first memory retention, and plugs into MCP clients like Claude Desktop, Cursor, and Windsurf.
      7
      MIT

    • NervaPack

      ramdhavepreetam
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to retrieve hyper-targeted, token-efficient context from a codebase by querying a locally built AST knowledge graph, and to persist cross-session agent memory through 17 MCP tools. All indexing and retrieval run entirely offline, so proprietary code never leaves the machine.
      80 PyPI
      1
      MIT

    • cortex

      Buzburg
      A
      license
      B
      quality
      A
      maintenance
      Enables AI coding agents and local LLMs to store and recall project memory, compact verbose logs, look up code symbols, create and rewind workspace snapshots, detect risky commands and loops, pack context optimally, and draft tokens through MCP tools.
      10
      2
      Apache 2.0

    • jev-super-agent

      Kadihx
      A
      license
      A
      quality
      B
      maintenance
      Enables coding agents to make offline, zero-cost decisions using schema-safe Choice/Score/Noul primitives, a confidence gatekeeper, planning, adversarial red-teaming, research, and RLVR-based self-improvement via 21 MCP tools.
      24
      4
      MIT

    • flaiwheel

      dl4rce
      A
      license
      A
      quality
      A
      maintenance
      Self-hosted memory and governance layer for AI coding agents. 28 MCP tools with hybrid search, structured knowledge capture, behavioral nudges, and git-native storage. Zero cloud dependencies.
      30
      6
      Business Source 1.1

    • Claude Soul

      SalmaMaxwell
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables persistent cross-session memory, correction-pattern tracking, and self-evolving behavioral frameworks, so past facts and decisions stay searchable by meaning and recurring mistakes fade over time. Runs entirely locally through 15 MCP tools plus hooks, with optional semantic search via Ollama embeddings and no cloud or API key required.
      6 npm
      MIT
    Deploy Server
    Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    C2.4/5.0

    Scored across 62 tools

    Disambiguation2/5

    Several clusters of tools have unclear boundaries: knowledge_search vs knowledge_retrieve vs retrieve_exemplars, memory_recall vs memory_context vs memory_list, and webfetch vs browser_fetch all overlap in purpose. The four init_* tools (init_plan, init_task, init_agents, init_audit) and decision_classify vs model_decision are near-duplicates that an agent could easily misselect.

    Naming Consistency3/5

    There are strong consistent namespaces (knowledge_*, memory_*, task_*), but the surface also mixes bare verb_noun names (get_model_profile, set_model, ingest_procedure, score_compliance, run_verification) with un-prefixed concepts like webfetch, self_critique, and cognitive_status. It is readable but not a single predictable convention.

    Tool Count1/5

    At 62 tools this far exceeds a well-scoped surface for a knowledge/memory/task assistant, and many tools are redundant or niche (four init_* variants, two fetch tools, three decision/health tools). The count indicates scope creep rather than a tight, purposeful set.

    Completeness4/5

    The domain surface is broad and mostly covers the lifecycle: knowledge ingest/search/list/delete/reindex/backup, full memory CRUD plus consolidation, and a fairly complete task lifecycle with plan and procedure support. Minor gaps remain, such as no document edit/update operation and procedures lacking delete/update beyond block versioning, with backup restore only available offline.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources