I Gave Two TypeScript Agent Sessions One Shared Memory With Hindsight (No LLM Key)

说明与用途

Hindsight 允许在没有 LLM 密钥的情况下持久化并检索代理关于 shop‑api 仓库的知识，加速后续会话。

问题

Agents lose contextual knowledge between sessions, leading to repeated discovery of repo conventions and hidden constraints.

结果

Hindsight successfully stored and retrieved five facts about the shop‑api repo in no‑LLM mode, with zero token usage and fast query times.

工作流

• Install Hindsight API server via pip in a Python 3.12 virtual environment
• Configure Hindsight to run in no‑LLM mode with HINDSIGHT_API_LLM_PROVIDER=none
• Start the server and note startup times and resource usage
• Create a TypeScript client with @vectorize-io/hindsight-client
• In Agent A script, create a bank and retain five domain facts
• In Agent B script, instantiate a new client and query the bank with four questions
• Observe that answers are retrieved from stored facts without LLM usage

证据

Hindsight documents a mode for exactly that, so this is a test of its no-LLM floor, not of everything it can do.

来源

The five retains took 184, 42, 46, 56 and 41 ms. Every response reported zero LLM tokens, which is expected with no model.

来源

The startup banner showed v0.10.2 with an embedded PostgreSQL (pg0, started automatically), LLM none / none, local embeddings (BAAI/bge-small-en-v1.5), a local reranker (cross-encoder/ms-marco-MiniLM-L-6-v2), and MCP enabled at /mcp.

来源