AgentIndex icon
AgentIndex
engram-mcp logo
engram-mcp
★ 18
vs
sense logo
sense
★ 40

engram-mcp vs sense

engram-mcp: Engram is an MCP server that provides persistent, Git-aware session memory for coding agents, allowing structured handoffs between sessions and branches. It helps agents retain context, decisions, and tasks, backed by local SQLite and ONNX embeddings without cloud dependencies.; sense: Sense is an MCP server designed to provide AI coding agents with a deep structural understanding of codebases. It indexes repositories locally, offering tools like symbol graph, semantic code search, and convention detection to enhance agent efficiency and accuracy.

01

TL;DR

engram-mcp logo
engram-mcpMemory & Context · ★ 18

Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover.

Read engram-mcp full review →
sense logo
senseMemory & Context · ★ 40

Enable AI agents to efficiently answer structural code questions like 'who calls this function?' by using pre-computed graphs.

Read sense full review →
02

Side-by-Side Comparison

Field
engram-mcp logoengram-mcp
sense logosense
Category
Memory & Context
Memory & Context
Stars
★ 18
★ 40
License
Apache-2.0
MIT
Install Command
cargo install engram_mcp
curl -fsSL https://luuuc.github.io/sense/install.sh | sh
Updated
5d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
Git-aware Memory, Coding Agent Tools, Context Management
AI Coding Agents, Codebase Context, Symbol Graph
03

Features

engram-mcp logoengram-mcp
01Provides Git-aware session memory that scopes context to specific git branches, preventing information leakage.
02Enables structured session handoffs to capture summaries, decisions, todos, blockers, and mental models for continuity.
03Offers local-first persistent storage using SQLite and ONNX embeddings, ensuring no cloud or LLM calls are needed for storage.
04Features advanced memory retrieval with hybrid scoring (cosine, recency, importance), hierarchical clustering, and branch-aware queries.
05Includes automated memory management capabilities such as decay, semantic deduplication, and auto-pruning of low-relevance memories.
sense logosense
01Provides symbol relationships, callers, callees, inheritance, tests, and dead code detection via `sense_graph`.
02Offers hybrid semantic code search (`sense_search`) with bi-encoder, cross-encoder, keyword, and text fallback.
03Calculates blast radius, affected code, affected tests, and risk score using `sense_blast`.
04Detects project-specific coding conventions from source via `sense_conventions` for style adherence.
04

Use Cases

engram-mcp logoengram-mcp
↳Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover.
↳Automatically retrieve relevant context and prior session details when resuming work on the same or a different Git branch.
↳LLM agents can proactively load relevant memories at the start of a conversation, building context from recent Git activity.
↳Passively capture coding decisions and session summaries into memory through integrated hooks without explicit tool calls.
↳Maintain a centralized, searchable, and structured memory of project-specific decisions, recurring patterns, and past debug solutions.
sense logosense
↳Enable AI agents to efficiently answer structural code questions like 'who calls this function?' by using pre-computed graphs.
↳Reduce AI agent tool calls, token usage, and session time, leading to significant cost and time savings for code-related tasks.
↳Help AI agents write code that adheres to specific project conventions and styles, improving code quality and consistency.
↳Perform advanced code analysis such as identifying dead code or understanding the blast radius of changes.
FAQ

FAQ

What is the difference between engram-mcp and sense?
Both engram-mcp and sense are in the Memory & Context category. engram-mcp has 18 stars, while sense has 40 stars.
Which is better, engram-mcp or sense?
The best choice depends on your use case. Choose engram-mcp if Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover., and sense if Enable AI agents to efficiently answer structural code questions like 'who calls this function?' by using pre-computed graphs..
Is engram-mcp free or open source?
Yes, engram-mcp is open source on GitHub (Apache-2.0).
Is sense free or open source?
Yes, sense is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to engram-mcp →Alternatives to sense →engram-mcp details →sense details →