My AI agents were choking on their own markdown logs. I gave them a database.

说明与用途

AI 代理因大量 Markdown 日志失去上下文。PentaCore 是一个基于 Rust 的 SQLite 服务器，存储结构化笔记和实体，快速恢复上下文，避免重复失败，并在子代理之间共享决策。

问题

AI agents accumulated markdown logs that exceeded the 256k token context window, causing restarts, loss of progress, repeated failures, and lack of shared state between subagents.

结果

Agents no longer choke on logs; context is restored with minimal tokens, failures are avoided, subagents receive decisions, and overall progress is summarized in a single query.

工作流

• 1. Capture agent actions and results as structured notes and entities in PentaCore.
• 2. Store failures as marked checks to prevent repeats.
• 3. Propagate top-level decisions to subagents via shared entity status.
• 4. Use single queries (e.g., query_entities) to retrieve pending tasks or overall status.
• 5. On session start, call resume(task) to restore minimal context needed for continuation.

证据

Agents produce logs at every step: what they found, what they tried, what failed. All of that was landing in markdown files.

来源

I did not find a tool that fit. So I built one: PentaCore, an MCP server in Rust. One binary, one encrypted SQLite file.

来源

Now "what has not been checked yet" is one call: {"name":"query_entities",...}

来源