Hindsight: Agent Memory That Learns

★ 61,195⑂ 7,369👁 115⑃ 4,463● 1,978▤ 76
PythonMITCreated 2025-10-30hindsight.vectorize.io/
Download: v1.2.1v1.2.1 ↓1.2.12026-11-10
+155
Daily
+1,201
Weekly
61,195
stars
7,369
forks
115
watchers
4,463
prs
1,978
issues
76
releases

README

!Hindsight Banner

Documentation • Integrations • Cookbook • Benchmarks • Paper • Hindsight Cloud









  




---

 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.

 🆕 Introducing Hindsight Models: decision, rerank and embedding models built for agent memory. Open weights on Hugging Face, or hosted on Hindsight Inference. Read the post →

Contents

- Memory Performance & Accuracy
- Quick Start — server · clients · platforms · embedded
- Adding Hindsight to Your Agent — LLM Wrapper · integrations · coding agents · MCP
- Core Concepts — memory types · retain / recall / reflect · observations · mental models & pages · decision models · banks
- Use Cases
- Running in Production
- Resources

---

 Memory Performance & Accuracy

Hindsight is the most accurate agent memory system ever tested according to benchmark performance. It has achieved state-of-the-art performance on the LongMemEval benchmark, widely used to assess memory system performance across a variety of conversational AI scenarios. The current reported performance of Hindsight and other agent memory solutions as of January 2026 is shown here:

!Overview

 Live, continuously updated results — including per-model accuracy, latency and cost — are published at benchmarks.hindsight.vectorize.io.

The benchmark performance data for Hindsight has been independently reproduced by research collaborators at the Virginia Tech Sanghani Center for Artificial Intelligence and Data Analytics and The Washington Post. Other scores are self-reported by software vendors.

Hindsight is being used in production at Fortune 500 enterprises and by a growing number of AI startups.

---

 🤖 Using a coding agent? Install the Hindsight documentation skill for instant access to docs while you code:
 bash
 npx skills add https://github.com/vectorize-io/hindsight --skill hindsight-docs
 
 Works with Claude Code, Cursor, and other AI coding assistants.

---

 Quick Start

 1. Start a server

 Docker (recommended)

bash
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


API: http://localhost:8888
UI: http://localhost:9999

Hindsight works with 25+ LLM providers via HINDSIGHT_API_LLM_PROVIDER — hosted (openai, anthropic, gemini, groq, bedrock, vertexai, minimax, deepseek, atlas, meta, …), fully local (ollama, lmstudio, llamacpp), any OpenAI-compatible endpoint, and gateways (litellm, litellmrouter) that reach the rest. Existing subscriptions work too: openai-

Top issues

Discussions

Latest release

v1.2.1 v1.2.1 2026-11-10
What's Changed
 docs drop 0.9 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/6284
 docs: reading progress bar under the navbar by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/6285
 fix(admin): hindsight-admin cloud is listed in --help by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/6286
 fix(api): one id rule for banks, aliases and mental models; bound page max_tokens by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/6282
 fix(coding-agents): survey starts from every host again; keep terminal-manager env and color codes

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON