Show HN：Aegis Memory – 開源多代理AI系統的記憶層
Aegis Memory 是一個開源、生產級的記憶引擎，專為多代理AI系統設計，透過語義搜尋和ACE模式實現持久學習。它支援自行託管，並採用Apache 2.0授權。
Navigation Menu
Search code, repositories, users, issues, pull requests...
Provide feedback
We read every piece of feedback, and take your input very seriously.
Saved searches
Use saved searches to filter your results more quickly
To see all available qualifiers, see our documentation.
Memory engine for multi-agent AI systems. ACE patterns for persistent learning. Production-ready, self-hostable, Apache 2.0.
License
Uh oh!
There was an error while loading. Please reload this page.
quantifylabs/aegis-memory
Folders and files
Latest commit
History
Repository files navigation
Aegis Memory
The memory engine for multi-agent systems.
Aegis Memory is a production-ready, self-hostable memory engine designed to give AI agents a persistent learning loop. By combining semantic search, scope-aware access control, and ACE (Agentic Context Engineering), Aegis allows agents to share state, vote on strategies, and extract actionable reflections from their failures.
Quick Start
1. Start the Server (2 min)
2. Install the CLI + SDK
3. Configure & Use
CLI Reference
Aegis provides a powerful CLI for all memory operations:
→ Full CLI Reference
Python SDK
Why Aegis Memory?
Aegis Memory is not just another vector database. It's an active strategy engine with primitives designed to turn agent execution into persistent organizational intelligence.
Features
Core Memory
ACE Patterns
Production Ready
Framework Integrations
Drop-in support for popular agent frameworks:
→ Integration Guides
ACE Patterns
Aegis implements patterns from recent research on self-improving agents:
Memory Voting
Session Progress
→ ACE Patterns Guide
Performance
Documentation
Deployment
Docker Compose
Kubernetes
Configuration
→ Full Configuration
Contributing
We welcome contributions! See CONTRIBUTING.md for guidelines.
License
Apache 2.0 — Use it however you want. See LICENSE.
Links
Built with ❤️ for the agent community
About
Memory engine for multi-agent AI systems. ACE patterns for persistent learning. Production-ready, self-hostable, Apache 2.0.
Resources
License
Contributing
Uh oh!
There was an error while loading. Please reload this page.
Stars
Watchers
Forks
Releases
Packages
0
Contributors
2
Languages
Footer
Footer navigation
相關文章