by Goldentrii · MCP Server · ★ 307
AgentRecall Your agent doesn't just remember. It learns how you think. Every correction saved is a mistake never repeated. Every insight compounded is tokens never wasted rebuilding context. Persistent, compounding memory + automatic correction capture. MCP server + SDK + CLI. <img src="https://img.shields.io/badge/Obsidian-compatible-7
| Stars | 307 |
| Forks | 52 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 66.6190990497022/100 |
| Open Issues | 26 |
| Last Updated | 2026-07-05 |
| Created | 2026-03-24 |
| Platforms | claude-code, cli, mcp, node |
| Est. Tokens | ~25k |
These tools work well together with AgentRecall-MCP for enhanced workflows:
Explore other popular mcp server tools:
AgentRecall-MCP is Correction-first persistent memory for AI agents. MCP server + SDK + CLI. Compounds across sessions.. It is categorized as a MCP Server with 307 GitHub stars.
AgentRecall-MCP is primarily written in JavaScript. It covers topics such as agent-learning, agent-memory, ai-memory-systems.
You can find installation instructions and usage details in the AgentRecall-MCP GitHub repository at github.com/Goldentrii/AgentRecall-MCP. The project has 307 stars and 52 forks, indicating an active community.
AgentRecall-MCP is released under the MIT license, making it free to use and modify according to the license terms.