AgentIndex icon
AgentIndex
sense logo
sense
★ 40
vs
mneme logo
mneme
★ 167

sense vs mneme

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.; mneme: dsh-mneme is a DeepSeek Harness plugin providing sophisticated cross-session memory for LLMs. It not only stores information but actively manages it through features like background deduplication, conflict resolution, and auditable history, ensuring AI remembers past interactions.

01

TL;DR

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 →
mneme logo
mnemeMemory & Context · ★ 167

Continuing project discussions across multiple sessions without repetition.

Read mneme full review →
02

Side-by-Side Comparison

Field
sense logosense
mneme logomneme
Category
Memory & Context
Memory & Context
Stars
★ 40
★ 167
License
MIT
MIT
Install Command
curl -fsSL https://luuuc.github.io/sense/install.sh | sh
dsh plugin --profile web add @modusensus/dsh-mneme && dsh web
Updated
2d ago
2d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
AI Coding Agents, Codebase Context, Symbol Graph
LLM Memory, Cross-Session Context, DeepSeek Harness Plugin
03

Features

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.
mneme logomneme
01Replayable and Auditable Memory
02Conflict Resolution with Human Oversight
03Agent and Workspace Memory Isolation
04Offline-first Local Semantic Search
05Automatic Background Memory Consolidation
04

Use Cases

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.
mneme logomneme
↳Continuing project discussions across multiple sessions without repetition.
↳Persisting AI's understanding of user preferences and coding habits long-term.
↳Automatic archiving and retrieval of organized research notes after closing chat windows.
FAQ

FAQ

What is the difference between sense and mneme?
Both sense and mneme are in the Memory & Context category. sense has 40 stars, while mneme has 167 stars.
Which is better, sense or mneme?
The best choice depends on your use case. Choose sense if Enable AI agents to efficiently answer structural code questions like 'who calls this function?' by using pre-computed graphs., and mneme if Continuing project discussions across multiple sessions without repetition..
Is sense free or open source?
Yes, sense is open source on GitHub (MIT).
Is mneme free or open source?
Yes, mneme 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 sense →Alternatives to mneme →sense details →mneme details →