Hindsight

Hindsight adds a memory component to AI agents so they can retain information across interactions.

github.com/vectorize-io/hindsight
Hindsight homepage screenshot

About Hindsight

Hindsight is an open source memory system for AI agents that retains information across interactions. It provides retain, recall, and reflect operations, with concepts including memory types, observations, mental models, knowledge pages, and banks.

It runs as a server via Docker with a local API and UI, and connects to 25+ LLM providers including hosted services, local models, and OpenAI-compatible endpoints. A documentation skill is available for coding assistants such as Claude Code and Cursor.

Key features

  • Retains information across agent interactions for later recall
  • Supports retain, recall, and reflect memory operations
  • Connects to 25+ LLM providers, including local models
  • Runs via Docker with local API and UI endpoints
  • Integrates with coding agents and MCP setups
  • Provides documentation skill for Claude Code and Cursor
Best for: Developers building AI agents that need memory across interactions.
Good for
  • Open source repository
  • Works with 25+ LLM providers including local models
  • Publishes live benchmark accuracy, latency and cost data

Hindsight at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

Hindsight alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Agents & Automation

Well-known listings from the same topic.

All 313

Hindsight FAQ

How can Hindsight be run locally?
Using Docker with configured LLM credentials, exposing an API on port 8888 and a UI on port 9999.
Which LLM providers are supported?
25+ providers via HINDSIGHT_API_LLM_PROVIDER, including hosted services, local options like Ollama, LM Studio and llama.cpp, OpenAI-compatible endpoints, and LiteLLM gateways.
Where are benchmark results available?
Live results including per-model accuracy, latency and cost are published at benchmarks.hindsight.vectorize.io.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing