DEV Community

Ramu Narasinga
Ramu Narasinga

Posted on

Hindsight, an Agent memory that learns.

#opensource #memory #llm #handsight

In this article, we review Hindsight. You will learn:

  1. What is Hindsight?

  2. Quickstart guide

  3. Adding Hindsight to your agent.

What is Hindsight?

Hindsight™ is an agent memory system built to create smarter agents that learn over time. Most agent memory systems focus on recalling conversation history. Hindsight is focused on making agents that learn, not just remember.

It eliminates the shortcomings of alternative techniques such as RAG and knowledge graph and delivers state-of-the-art performance on long term memory tasks.

Check out the demo video in README.

Quickstart guide

In the Hindsight README, I found four steps to get started quickly.

  1. Start a server 
export OPENAI_API_KEY=sk-xxx

docker run -it --pull always --name hindsight --restart unless-stopped -p 8888:8888 -p 9999:9999 \
  -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
  -v hindsight-data:/home/hindsight/.pg0 \
  ghcr.io/vectorize-io/hindsight:latest
Enter fullscreen mode Exit fullscreen mode
  1. Connect a client 
pip install hindsight-client -U                                  # Python
npm install @vectorize-io/hindsight-client                        # Node.js / TypeScript
go get github.com/vectorize-io/hindsight/hindsight-clients/go     # Go
curl -fsSL https://hindsight.vectorize.io/get-cli | bash          # CLI
Enter fullscreen mode Exit fullscreen mode

Below is an example showing this:

from hindsight_client import Hindsight

client = Hindsight(base_url="http://localhost:8888")

# Retain: Store information
client.retain(bank_id="my-bank", content="Alice works at Google as a software engineer")

# Recall: Search memories
client.recall(bank_id="my-bank", query="What does Alice do?")

# Reflect: Generate disposition-aware response
client.reflect(bank_id="my-bank", query="Tell me about Alice")
Enter fullscreen mode Exit fullscreen mode

Adding Hindsight to your agent

Below is a code snippet demonstrating how to add Hindsight to your existing LLM layer.

// install the hindsight-llm
pip install hindsight-litellm
Enter fullscreen mode Exit fullscreen mode 
from openai import OpenAI
from hindsight_litellm import wrap_openai

# Wrap your existing LLM client and you're done.
# Defaults to Hindsight Cloud; pass hindsight_api_url for a self-hosted server.
client = wrap_openai(
    OpenAI(),
    bank_id="user-123",
    hindsight_api_url="http://localhost:8888",
)

# Hindsight recalls relevant memories before the call
# and retains the conversation after it.
response = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[{"role": "user", "content": "What do you know about me?"}],
)
Enter fullscreen mode Exit fullscreen mode

You just have to wrap your LLM client as shown above and then memories are stored, retrived automatically on every call, with no other changes to code.

About me:

Hey, my name is Ramu Narasinga. Email: ramu.narasinga@gmail.com

I spent 3+ years studying OSS codebases and wrote 400+ articles on what makes the production-grade. Now I'm putting that into practice differently - instead of writing every fix myself, I run coding agents that do it.

How it works? Register your machine as a Runtime, point it at your repo. Agents pick up issues. write the fix, open the PR. You just review, they execute.

Build your coding agents and get more work done in less time at thinkthroo.com

References:

  1. github.com/vectorize-io/hindsight.

  2. hindsight.vectorize.io/.

  3. vectorize.io/.

Top comments (0)