Enterprise DNA
M MCP Servers Developer low

Perseus-Computing-LLC/perseus

by Various

The memory & context layer for AI agents: load only the context they actually need. Resolves live workspace state into verified facts before the context window opens. 94% fewer pro

P

MCP

Perseus-Computing-LLC/perseus

Added 13 July 2026

#agent-memory #ai-agents #claude-code #cli #context-engine #context-engineering #hermes #llm

Overview

Perseus is a memory and context layer for AI agents that loads only the context they actually need. It resolves live workspace state into verified facts before the context window opens, reducing prompt tokens by 94% with zero overhead. It provides 33 MCP tools and is local-first with an MIT license.

Best for

Best for
Developers building AI agents that need efficient context management

Use cases

  • Reducing prompt token usage for AI agents
  • Providing verified facts from live workspace state
  • Integrating with MCP tools for context management

How to use

Install

pip install perseus-ctx                       # 1. install

Tools exposed

  • perseus_services
  • perseus_read
  • perseus_list
  • perseus_tree
  • perseus_env
  • perseus_date
  • perseus_waypoint
  • perseus_session
  • perseus_focus
  • perseus_health
  • perseus_drift
  • perseus_memory
  • perseus_mimir
  • perseus_mneme
  • perseus_skills
  • perseus_include
  • perseus_agora
  • perseus_inbox
  • perseus_capture
  • perseus_context_diff

Tested with

Claude Desktop, Claude Code, Cursor

Notes

Perseus is a memory and context layer for AI agents that loads only the context they actually need. It resolves live workspace state into verified facts before the context window opens, reducing prompt tokens by 94% with zero overhead. It provides 33 MCP tools and is local-first with an MIT license.

21 stars on GitHub. Last updated 2026-07-13. Licensed MIT.

Use cases

  • Reducing prompt token usage for AI agents
  • Providing verified facts from live workspace state
  • Integrating with MCP tools for context management

Pros

  • 94% reduction in prompt tokens
  • Zero overhead (0 ms)
  • Local-first and open source (MIT)

Cons

  • Limited to Python environment
  • Relatively new with only 21 stars
  • Requires integration with existing AI agent workflows

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • 94% reduction in prompt tokens
  • Zero overhead (0 ms)
  • Local-first and open source (MIT)

Cons

  • Limited to Python environment
  • Relatively new with only 21 stars
  • Requires integration with existing AI agent workflows
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks