Skip to main content
Glama
DanceNitra

inspeximus

by DanceNitra
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to inspeximus

Related Servers

  • dakera-mcp by Dakera-AI

    dakera-mcpofficial

    Dakera-AI
    A
    license
    A
    quality
    B
    maintenance
    Self-hosted MCP-native agent memory server. Gives AI agents persistent, decay-weighted memory via 83 MCP tools — no cloud, full control. RocksDB+HNSW backend. Works with Claude Code, Cursor, and any MCP-compatible agent.
    14
    8
    MIT

  • verifiable-memory

    Mars-proj
    A
    license
    A
    quality
    D
    maintenance
    Memory for AI agents that can't hallucinate — answers only from stored facts with a citation, or honestly abstains. Provable forgetting (GDPR), valid-time, Merkle proofs, deterministic. MCP server, CPU-only, zero dependencies.
    13
    1
    MIT
  • Recall by RecallWorks

    Recallofficial

    RecallWorks
    A
    license
    Not graded
    quality
    C
    maintenance
    Open-source MCP memory server for AI agents — persistent, searchable, tiered memory across sessions. Works over stdio (Cursor, Claude Desktop) or HTTP+SSE. MIT licensed.
    8
    MIT

  • ForkMind

    Medhovarsh
    A
    license
    Not graded
    quality
    B
    maintenance
    Local-first MCP server that lets AI agents query their own LLM call history as a branchable DAG and offload conversation context into immutable, AES-256-GCM-encrypted capsules — restorable in full or per segment, crypto-shreddable, with RAID-style replication. 12 tools, no API keys, no cloud.
    56 npm
    3
    MIT

  • Remnic

    joshuaswarren
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first memory for AI agents: one store shared by Claude Code, Codex CLI, Cursor, Pi, Hermes, OpenClaw, and any MCP client. Plain markdown with YAML frontmatter on your disk, hybrid BM25 + vector recall with per-result provenance (Recall X-ray), a correction contract, and the MemCorrect benchmark.
    219
    MIT

  • NeverOnce

    WeberG619
    A
    license
    A
    quality
    C
    maintenance
    Persistent, correctable AI memory with zero dependencies. Corrections always surface first and never decay. SQLite-backed, 400 lines of pure Python, MCP server included.
    7
    3
    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

B3.4/5.0

Scored across 135 tools

Disambiguation2/5

With 135 tools, multiple families overlap heavily: recall/recall_iterative/recall_followup/recall_as/neighbors, consolidate/sleep/consolidate_clusters, remember/remember_decision/remember_in_partition/route, and numerous verify_*/check_*/record_*/report_* tools. The descriptions do draw distinctions, but the sheer surface makes misselection likely for an agent choosing among similar-sounding operations.

Naming Consistency3/5

Tool names are almost entirely snake_case, which is consistent at the casing level. However, the naming pattern is mixed: verb_noun (remember_decision, verify_writes), noun-only (provenance, history, coverage), and noun_register/report (risk_register, erasure_report, governance_report) all coexist without a single predictable convention.

Tool Count1/5

A 135-tool MCP surface is an extreme mismatch for practical agent use, far exceeding the 25-tool threshold for 'heavy'. While many tools are specialized governance or audit operations, the set is overwhelming and requires the agent to reason over an unusually large namespace.

Completeness5/5

The tool surface covers memory lifecycle (remember, get, recall, forget, revert), supersession, erasure and retention, access control/grants, partitions, audit trails, compliance reporting, and tamper-evidence checks. No obvious core gap exists; if anything, the domain is covered beyond what a typical MCP client can comfortably consume.

Maintenance

ActivityActive
ResponsivenessSlow

Resources