emem
Active·★ 72·Apache-2.0·Updated 2026-10-20
emem provides a shared, verifiable memory layer for multi-agent systems, ensuring that agents can cite and verify the same signed facts independently, regardless of their models, vendors, or trust boundaries. It stores facts as small, signed, content-addressed records, enabling them to survive context compaction, model swaps, and cross-agent hand-offs without drift.
#Multi-Agent#Shared Memory#Verifiable Data#Content-Addressed#AI Agents#Global Protocol#Earth Observation
01
Features
01Enables shared, verifiable memory for multi-agent systems.
02Stores facts as small, signed, content-addressed records with permanent addresses.
03Allows offline verification of any fact without trusting sender or server.
04Ensures facts survive context compaction, session ends, and model swaps, preserving precision.
05Facilitates trustless agreement and auditability of facts between independent agents.
02
Compatibility
Python
Runtime
Verified via docs
TypeScript
Runtime
Verified via docs
REST API
API Access
Verified via docs
MCP
Agent Protocol
Verified via docs
Docker
Deployment
Verified via docs
Agent Frameworks
Integration
Verified via docs
03
Quick start
1
$ pip install ememdev
04
Use cases
↳Preserve verified precision across long tasks, session ends, or model swaps.
↳Enable agreement on facts between agents from different organizations without shared trust.
↳Audit claims with verifiable facts long after their author is gone.
↳Perform complex value-predicate queries, ranking, filtering, and aggregation over geographical data.
05
Alternatives
pydantic-deepagents★ 1.1k
Python Deep Agent framework built on top of Pydantic-AI designed to help you quickly build production-grade autonomous agents with planning, filesystem operations, subagent delegation, and skills.
agent-manager★ 615
The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.
Agenvoy★ 509
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
squadra★ 334
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
Comments
Log in to leave a comment
No comments yet. Be the first!