sciver

MCPOfficialVectorize

Hindsight

Agent memory that learns from experience: it retains, recalls and reflects.

Vectorize’s Hindsight server stores facts, the agent’s experiences and the observations drawn from them in memory banks, and every bank has a built-in MCP endpoint with the retain, recall and reflect tools. It runs in Docker and needs a language model: an API key, a local model (such as Ollama) or an existing subscription; a separate package wires project memory into Claude Code, Codex and Cursor.

Installation

Manual install

$docker run -it --pull always --name hindsight --restart unless-stopped -p 8888:8888 -p 9999:9999 -e HINDSIGHT_API_LLM_API_KEY=<API_KEY> -v hindsight-data:/home/hindsight/.pg0 ghcr.io/vectorize-io/hindsight:latest

Details

Works in
Claude Code, Claude, Cursor, Codex, Gemini CLI, VS Code, Windsurf, Zed
Transport
local
License
MIT
Tasks
Research, Code
Rating
Source
github.com/vectorize-io/hindsight (opens in a new tab)

Tags

  • memory
  • learning
  • context
  • agents

Log in to rate

A pack is your own set of skills and MCP servers. sciver loads it in your AI with one command.

View in the library