Skip to main content

Hindsight Blog

Updates, insights, and deep dives into agent memory

Hindsight Cloud

News and updates from Hindsight Cloud

Hindsight

Releases, guides, and deep dives into agent memory

Pydantic AI Persistent Memory: Add It in 5 Lines of Code

Pydantic AI Persistent Memory: Add It in 5 Lines of Code

If you have built an AI agent with Pydantic AI, you already know it handles typed outputs, dependency injection, and async workflows well. But there is one thing it does not do: remember anything between runs. Every call to agent.run() starts with a blank slate. Your agent has no idea what the user said yesterday, what preferences they shared, or what it already researched.

Mar 9, 202613 min read
The Memory Upgrade Every OpenClaw User Needs

The Memory Upgrade Every OpenClaw User Needs

TL;DR

Mar 6, 202612 min read
Give Your OpenAI App a Memory in 5 Minutes

Give Your OpenAI App a Memory in 5 Minutes

Build a ChatGPT-style chatbot with persistent memory using the OpenAI SDK and Hindsight. Three API calls — retain(), recall(), reflect() — and your app remembers users across restarts, no vector database or RAG pipeline required.

Mar 5, 20265 min read
What's new in Hindsight 0.4.16

What's new in Hindsight 0.4.16

New features and improvements in Hindsight 0.4.16

Mar 5, 20263 min read
The Open-Source MCP Memory Server Your AI Agent Is Missing

The Open-Source MCP Memory Server Your AI Agent Is Missing

AI agents forget everything between sessions. Hindsight gives them persistent, structured memory via MCP. One Docker command to run the full stack locally. Connect any MCP-compatible client. Three core operations: retain (store), recall (search), reflect (reason) — plus mental models that auto-update as memories grow.

Mar 4, 202610 min read
I Gave 100+ LLMs a Permanent Memory With One Python Package

I Gave 100+ LLMs a Permanent Memory With One Python Package

hindsight-litellm adds persistent memory to any LLM provider via LiteLLM — OpenAI, Anthropic, Groq, Azure, Bedrock, Vertex AI, and 100+ more. Three lines of setup, and every LLM call automatically gets context from past conversations.

Mar 3, 20266 min read
What's new in Hindsight 0.4.15

What's new in Hindsight 0.4.15

New features and improvements in Hindsight 0.4.15

Mar 3, 20267 min read
Your CrewAI Agents Forget Everything Between Runs. Here's the Fix.

Your CrewAI Agents Forget Everything Between Runs. Here's the Fix.

CrewAI agents lose all memory when a crew finishes. hindsight-crewai plugs into CrewAI's ExternalMemory to persist knowledge across runs -- three lines of setup, and your agents automatically store task outputs and recall relevant context.

Mar 2, 20266 min read
What's new in Hindsight 0.4.13 and 0.4.14

What's new in Hindsight 0.4.13 and 0.4.14

New features and improvements in Hindsight 0.4.13 and 0.4.14

Feb 27, 20265 min read