by plastic-labs · Agent Tool · ★ 3.9k
Honcho is an open source memory library with a managed service for building stateful agents. Use it with any model, framework, or architecture. It enables agents to build and maintain state about any entity--users, agents, groups, ideas, and more. And because it's a continual learning system, it understands entities that change over time. Using Honcho as your memory system will earn your agents higher retention, more trust, and help you build data moats to out-compete incumbents. Honcho has defined the Pareto Frontier of Agent Memory.
| Stars | 3,887 |
| Forks | 458 |
| Language | Python |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 54.572/100 |
| Open Issues | 100 |
| Last Updated | 2026-05-21 |
| Created | 2023-09-10 |
| Platforms | python |
| Est. Tokens | ~1238k |
These tools work well together with honcho for enhanced workflows:
Explore other popular agent tool tools:
honcho is Memory library for building stateful agents. It is categorized as a Agent Tool with 3.9k GitHub stars.
honcho is primarily written in Python. It covers topics such as agent-memory, ai, ai-agents.
You can find installation instructions and usage details in the honcho GitHub repository at github.com/plastic-labs/honcho. The project has 3.9k stars and 458 forks, indicating an active community.
honcho is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.