Mnemo (Greek: memory) gives AI assistants like Claude access to large codebases, documentation sites, PDFs, and more by leveraging Gemini's 1M token context window and context caching features.
Why Mnemo?
Instead of complex RAG pipelines with embeddings and retrieval, Mnemo takes a simpler approach:
Load your entire codebase into Gemini's context cache
Query it with natural language
Let Claude orchestrate while Gemini holds the context
This gives you:
Perfect recall - no chunking or retrieval means no lost context
Lower latency - cached context is served quickly
Cost savings - cached tokens cost 75-90% less than regular input tokens
Simplicity - no vector databases, embeddings, or complex retrieval logic
Mnemo can be deployed in three ways depending on your needs.
Option 1: Local Server (Development & Full Features)
Best for development and when you need to load local files.
# Clone and install
git clone https://github.com/Logos-Flux/mnemo
cd mnemo
bun install
# Set your Gemini API key
export GEMINI_API_KEY=your_key_here
# Start the server
bun run dev
# Load a GitHub repo
curl -X POST http://localhost:8080/tools/context_load \
-H "Content-Type: application/json" \
-d '{"source": "https://github.com/honojs/hono", "alias": "hono"}'
# Load a documentation site (crawls up to token target)
curl -X POST http://localhost:8080/tools/context_load \
-H "Content-Type: application/json" \
-d '{"source": "https://hono.dev/docs", "alias": "hono-docs"}'
# Load a PDF
curl -X POST http://localhost:8080/tools/context_load \
-H "Content-Type: application/json" \
-d '{"source": "https://arxiv.org/pdf/2303.08774.pdf", "alias": "gpt4-paper"}'
# Load a private repo (with GitHub token)
curl -X POST http://localhost:8080/tools/context_load \
-H "Content-Type: application/json" \
-d '{"source": "https://github.com/owner/private-repo", "alias": "private", "githubToken": "ghp_xxx"}'
# Load multiple sources into one cache
curl -X POST http://localhost:8080/tools/context_load \
-H "Content-Type: application/json" \
-d '{"sources": ["https://github.com/owner/repo", "https://docs.example.com"], "alias": "combined"}'
# Query the cache
curl -X POST http://localhost:8080/tools/context_query \
-H "Content-Type: application/json" \
-d '{"alias": "hono", "query": "How do I add middleware?"}'
# List active caches
curl -X POST http://localhost:8080/tools/context_list \
-H "Content-Type: application/json" -d '{}'
# Get usage stats with cost tracking
curl -X POST http://localhost:8080/tools/context_stats \
-H "Content-Type: application/json" -d '{}'
# Evict when done
curl -X POST http://localhost:8080/tools/context_evict \
-H "Content-Type: application/json" \
-d '{"alias": "hono"}'
CLI
Note: the mnemo CLI requires either npm install -g @mnemo/local (once published) or running bun run build from the repo root and then invoking bun packages/local/dist/cli.js … directly. Until v0.2.0 is on npm, use the local clone path.
# Start server
mnemo serve
# Start MCP stdio transport (for Claude Desktop)
mnemo stdio
# Load a project
mnemo load ./my-project my-proj
# Query
mnemo query my-proj "What's the main entry point?"
# List caches
mnemo list
# Remove cache
mnemo evict my-proj
MCP Tools
Tool
Description
context_load
Load GitHub repos, URLs, PDFs, or local dirs into Gemini cache
context_query
Query a cached context with natural language
context_list
List all active caches with token counts and expiry
context_evict
Remove a cache
context_stats
Get usage statistics with cost tracking
context_refresh
Reload a cache with fresh content
context_load Parameters
Parameter
Description
source
Single source: GitHub URL, any URL, or local path
sources
Multiple sources to combine into one cache
alias
Friendly name for this cache (1-64 chars)
ttl
Time to live in seconds (60-86400, default 3600)
githubToken
GitHub token for private repos
systemInstruction
Custom system prompt for queries
Configuration
Variable
Description
Default
GEMINI_API_KEY
Your Gemini API key
Required
MNEMO_PORT
Server port (local only)
8080
MNEMO_DIR
Data directory (local only)
~/.mnemo
MNEMO_AUTH_TOKEN
Auth token for protected endpoints
None
Optional (Cloudflare Worker deploy):
Variable
Description
Default
CLOUDFLARE_ACCOUNT_ID
Cloudflare account ID for wrangler deploy
None
CLOUDFLARE_API_TOKEN
Cloudflare API token with Workers edit permission
None
Authentication
When MNEMO_AUTH_TOKEN is configured, the /mcp and /tools/* endpoints require authentication:
# Set auth token (Workers)
bunx wrangler secret put MNEMO_AUTH_TOKEN
# Requests must include header:
Authorization: Bearer your-token-here
You always pay for Gemini API usage regardless of deployment option. Mnemo uses Gemini's context caching which is significantly cheaper than standard input:
Resource
Cost
Cache storage
~$4.50 per 1M tokens per hour
Cached input
75-90% discount vs regular input
Regular input
~$0.075 per 1M tokens (Flash)
Example: 100K token codebase cached for 1 hour with 10 queries ≈ $0.47
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Perguntas
Como instalo Mnemo?
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Mnemo precisa de uma chave de API?
Este registro não lista nenhuma variável de ambiente obrigatória.
Qual transporte Mnemo usa?
Mnemo roda localmente via stdio.
Quando Mnemo foi verificado pela última vez?
Última verificação: 2026-10-28. MCP server that uses Gemini's context caching as extended memory for AI assistants. Load GitHub repos, URLs, PDFs.