context-mode
★ 31.8k
vs
enquire-mcp
★ 34
context-mode vs enquire-mcp
context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.; 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
context-modeMemory & Context · ★ 31.8k
When to choose:
- Your sessions fill up with tool output such as Playwright snapshots, GitHub issue lists or logs.
- You want work state (edits, git operations, tasks, decisions) to survive context compaction without being dumped back into the window.
- You use a hook-capable agent, where tool routing happens automatically.
When to skip:
- You need an OSI open-source licence: it uses the Elastic License 2.0, which restricts uses such as offering it as a managed service.
- Your sessions are short and rarely hit the context limit.
- You do not want hooks changing how your agent's tools behave.
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
context-modeenquire-mcpCategory
Memory & Context
Memory & Context
Stars
★ 31.8k
★ 34
License
Elastic License 2.0
MIT
Install Command
npm install -g context-mode
npm install -g @oomkapwn/enquire-mcp
Updated
1d ago
1d ago
Open Source
Yes
Yes
Tags
antigravity, claude, claude-code
AI Agents, Long-term Memory, RAG
03
Features
context-mode01Context Saving: Sandbox tools keep raw data out of the context window, achieving up to 98% reduction.
02Session Continuity: Tracks every file edit, git operation, task, and user decision in SQLite for seamless session resume.
03Think in Code: Promotes LLMs to program analysis, not compute it, saving 100x context by logging only results.
04Batch Execution & Search: Run multiple commands/queries in one call with tools like `ctx_batch_execute`.
05Advanced Knowledge Base: Uses SQLite FTS5 with BM25 ranking, smart snippets, and TTL cache for efficient information retrieval.
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
context-mode↳Deep repository research and analysis (e.g., architecture, contributors, issues)
↳Analyze Git history to identify top contributors, commit frequency, and most changed files
↳Efficiently process large JSON APIs, web pages, or logs without flooding the context window
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
context-modeMost PopularTrending
enquire-mcp—
FAQ
FAQ
What is the difference between context-mode and enquire-mcp?
Both context-mode and enquire-mcp are in the Memory & Context category. context-mode has 31.8k stars, while enquire-mcp has 34 stars.
Which is better, context-mode or enquire-mcp?
The best choice depends on your use case. Choose context-mode if Deep repository research and analysis (e.g., architecture, contributors, issues), 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 context-mode free or open source?
Yes, context-mode is open source on GitHub (Elastic License 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.
→