letta
★ 25.2k
vs
enquire-mcp
★ 34
letta vs enquire-mcp
letta: Letta is a powerful platform for building stateful AI agents equipped with advanced memory, enabling them to learn and self-improve over time. It provides both a command-line interface for local agent execution and a comprehensive API with Python and TypeScript SDKs for seamless integration into applications.; enquire-mcp: enquire-mcp transforms your Obsidian vault into persistent, queryable long-term memory for various AI agents, eliminating the need to re-explain context in every session. It provides best-in-class hybrid retrieval, including semantic search, reranking, and HNSW, all running locally with zero cloud calls during serving.
01
TL;DR
lettaMemory & Context · ★ 25.2k
When to choose:
- You want a long-lived agent that remembers past work and rewrites its own memory and context over time.
- You want one agent reachable from CLI, desktop, browser, mobile and messaging apps, with subagents, schedules and hooks.
- You want memory you can inspect: the README says context is tracked in git and can sync to your own repository.
When to skip:
- You only need to add memory to an agent you already use through MCP; a small MCP memory server is a lighter fit.
- You rely on older Letta tutorials or the V1 API server: the project restructured, and the V1 server is retired.
- You want everything to work without signing in: Letta Cloud is the default backend and some features need it.
enquire-mcpMemory & Context · ★ 34
Long-term memory for AI agents: Provides durable, semantic recall for agents across sessions, models, and providers, grounded in your Obsidian notes.
02
Side-by-Side Comparison
Field
lettaenquire-mcpCategory
Memory & Context
Memory & Context
Stars
★ 25.2k
★ 34
License
Apache-2.0
MIT
Install Command
npm install -g @letta-ai/letta-code
npm install -g @oomkapwn/enquire-mcp
Updated
5d ago
1d ago
Open Source
Yes
Yes
Tags
Stateful AI, Agent Platform, Advanced Memory
AI Agents, Long-term Memory, RAG
03
Features
letta01Build stateful AI agents with advanced memory
02Agents capable of learning and self-improvement over time
03CLI tool for running agents locally in your terminal
04Comprehensive API for integrating agents into applications
05Support for skills and subagents; fully model-agnostic
enquire-mcp01Vendor-neutral memory: Your memory lives in .md files, ensuring portability across different AI agents and providers.
02Best-in-class hybrid retrieval: Features BM25, multilingual embeddings, BGE cross-encoder reranker, HNSW, and int8 quantization for superior search quality and performance.
03Zero cloud calls during serve: All models are cached locally, and vault content never leaves your machine, ensuring privacy and air-gap safety.
04Freshness-aware recall: Search hits report note age and a `stale` flag, with optional recency-weighted ranking to prioritize fresh knowledge.
05PDFs with OCR & GraphRAG-light: Integrates PDFs (including OCR for scanned docs) into hybrid search and offers GraphRAG-light for wikilink community detection.
04
Use Cases
letta↳Running AI agents locally in your terminal for coding and general tasks.
↳Integrating stateful AI agents into custom applications using the API and SDKs.
↳Developing self-improving AI systems that adapt and learn continually.
enquire-mcp↳Long-term memory for AI agents: Provides durable, semantic recall for agents across sessions, models, and providers, grounded in your Obsidian notes.
↳Personal knowledge base / second brain: Offers hybrid retrieval across 50+ languages, wikilink graph-boost, and GraphRAG-light to surface relevant notes and discover connections.
↳Agentic RAG / context engineering: Exposes per-signal scores, HyDE pre-rewrites, and sub-question decomposition for advanced retrieval, plus a built-in evaluation harness.
05
Best For
lettaMost PopularEssentialTrending
enquire-mcp—
FAQ
FAQ
What is the difference between letta and enquire-mcp?
Both letta and enquire-mcp are in the Memory & Context category. letta has 25.2k stars, while enquire-mcp has 34 stars.
Which is better, letta or enquire-mcp?
The best choice depends on your use case. Choose letta if Running AI agents locally in your terminal for coding and general tasks., and enquire-mcp if Long-term memory for AI agents: Provides durable, semantic recall for agents across sessions, models, and providers, grounded in your Obsidian notes..
Is letta free or open source?
Yes, letta is open source on GitHub (Apache-2.0).
Is enquire-mcp free or open source?
Yes, enquire-mcp is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→