Skip to main content
Glama
Sign In
Memoria MCP

Memoria MCP

by kolivritech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Memoria MCP (io.github.kolivritech/memoria-mcp)

Glama MCP Server Memoria Cloud LongMemEval Latency

Stop trusting probabilistic guesses. Give your AI coding agents deterministic long-term memory.

Memoria is a deterministic long-term memory and code intelligence MCP server for 15 AI coding clients: Claude Code, OpenCode, Cursor, Windsurf, VS Code (GitHub Copilot), Codex CLI, Gemini CLI, Zed, Cline, Roo Code, Kilo Code, Continue, Goose, Amp, and Claude Desktop.

Verified Benchmarks

Benchmark

Memoria Score

Latency / Cost

Comparison

LongMemEval (ICLR 2025, 500 questions)

500 / 500 (100.0%)

0.14 s / query · 0 LLM tokens

Supermemory 81.6% · Zep 71.2% · Mem0 ~67%

Multilingual LongMemEval (15 Languages incl. Hebrew)

102 / 102 (100.0%)

0 LLM tokens

Native RTL & multilingual symbolic reasoning

IntelBench Retrieval Latency

12.9 ms (83.3%)

Sub-15ms p50

15–150x faster than LLM write-wrappers

Synthetic Stress & Belief Revision (Supersedes)

5 / 5 (100.0%)

Deterministic

Outdated facts automatically superseded

Related MCP server: io.github.cdnsteve/sugar

30-Second Installation (All 15 AI Coding Clients)

  1. Get your free API key (1,000 free API calls & memories) at https://memoria.kolivri.com/register.

  2. Run the 1-line installer for macOS / Linux / WSL:

curl -fsSL https://memoria.kolivri.com/downloads/install.sh | MEMORIA_KEY=mem_dev_your_key_here bash

Or on Windows PowerShell:

$env:MEMORIA_KEY="mem_dev_your_key_here"; irm https://memoria.kolivri.com/downloads/install.ps1 | iex

Or add directly to Claude Code:

claude mcp add -s user --transport http memoria https://memoria.kolivri.com/v1/mcp --header "Authorization: Bearer mem_dev_your_key_here"

What Gets Configured Automatically

  • 30 Deterministic MCP Tools: encode_memory, batch_encode, recall_memories, build_context, forget_memory, delete_by_context, consolidate, feedback, health, stats, search_code, explain_code, find_references, find_file, explain_diff, explain_error, navigate, get_hierarchy, list_agent_wings, handoff_to_agent, and more.

  • 3 MCP Resources: memory://rules, memory://recent, memory://stats.

  • 8 Automatic Session Hooks: SessionStart, UserPromptSubmit, PostToolUse (Write, Edit, Read, TaskCreate, TaskCompleted), PreCompact, PostCompact, and Stop.

  • Multi-Agent Specialist Wings: Isolate and hand off architectural context across architect, reviewer, qa, security, and ops wings.

License

MIT © Kolivri Ltd

Tool Schema Changelog

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

Loading tool schema changelog…

    This server cannot be deployed

    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Sugar

      Benjaminn581
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI coding agents to read and write persistent, local-first memory across sessions and projects, with semantic search, global guidelines, and optional autonomous task execution.
      -

    • io.github.cdnsteve/sugar

      Sebastien94506
      F
      license
      Not graded
      quality
      A
      maintenance
      Gives AI coding agents persistent, local-first memory so they can store, semantically search, and recall decisions, preferences, error patterns, and cross-project guidelines directly during a session. It also optionally queues tasks for autonomous execution against that same memory.
      -

    • Sugar

      larry9154
      F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI coding agents to store and retrieve persistent project and cross-project memories via semantic search, so decisions, preferences, error patterns, and guidelines survive across sessions. Optionally supports autonomous task execution built on the same local-first knowledge store.
      -

    • knowledge-base-server

      huseyinhill
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to share a persistent, self-improving memory by ingesting sources like Obsidian vaults, code, transcripts, and session captures, then serving them back through search, classification, synthesis, and token-optimized context briefings. It lets multiple agents read and write the same knowledge base, so each session builds on the last without copy-pasting context.
      10 npm
      MIT