memory
Your OpenBot Agents Forget Between Threads. Give Them Shared Memory.
Connect an OpenBot agent to a Hindsight bank over MCP and its memory outlives the thread, survives compaction, and is shared with every teammate.
Four Things to Build With Vercel Eve and Hindsight
A team glossary that outlives the session, one customer across every channel, tenant isolation that is not a filter, and the memory your other AI tools already wrote.
How We Made Retain's Peak Memory Flat, from 4 MB to 90 MB Documents
How Hindsight 0.9.2 rebuilt the retain pipeline so peak memory stays flat from a 4 MB document to a 90 MB one, bounded by a budget instead of the input.
Hindsight 0.9.0: Knowledge Pages, and One Memory Plugin for Every Coding Agent
Hindsight 0.9.0 brings Knowledge Pages, documents your memory bank writes about itself, and one memory plugin for ten coding agents.
Give Aider a Memory That Outlives the Session
Aider is a sharp terminal pair programmer that forgets everything when it exits. hindsight-aider wraps the command so it recalls your project's decisions before each session and retains what it learns after.
Give Zed's AI Assistant a Persistent Memory
The Zed editor's AI assistant is sharp inside a task and a stranger between them. hindsight-zed gives it long-term memory that recalls and retains across sessions.
Teach Vercel Eve to Remember: Automatic Agent Memory
Vercel Eve agents get automatic long-term memory with hindsight-eve v0.2.0: context injected before every turn, each exchange saved after, no model tool call.
From Documents to Decisions: architxt and Hindsight
How architxt uses Hindsight as a time-aware agent memory layer to turn fragmented enterprise architecture documents into a queryable, current-state Temporal Mosaic.
Devin Desktop Persistent Memory (Formerly Windsurf)
Add persistent memory to Devin Desktop (formerly Windsurf): a remote MCP server plus one always-on rule that recalls at task start and retains as you work.
Entity Resolution in Agent Memory: One Person, Many Names
How agent memory decides that Sarah, Sarah Chen, and she are one person, and why Hindsight resolves entities with a co-occurrence graph, not embeddings.
Zapier Persistent Memory: Actions and Triggers
The Hindsight app for Zapier adds persistent memory to any Zap: Retain, Recall, and Reflect actions, plus triggers that start Zaps from memory events.
Structuring Chat Logs for Agent Memory
The shape of your chat logs decides your agent's memory quality. Retain whole conversations, label who is speaking, set context, and anchor in time.
Persistent Memory for the Vercel AI SDK in Five Tools
Add long-term memory to any Vercel AI SDK app with Hindsight. Five ready-to-use tools for retain, recall, and reflect that work with generateText, streamText, and ToolLoopAgent, on any model provider.
Hindsight Is Now a One-Click Memory Provider in the Hermes Desktop App
Hermes Agent's desktop app now lets you pick Hindsight as your memory provider and configure it entirely in-app — pick a mode, paste an API key, done. No config files, no .env editing. And it's the only memory backend that gets a full settings panel.
OpenHands (formerly OpenDevin) Forgets Every Task. Here's the One-Command Fix.
Add persistent long-term memory to OpenHands (formerly OpenDevin) with Hindsight. One command wires the Hindsight MCP server into config.toml and drops a recall/retain rule into AGENTS.md, so the agent recalls relevant context at the start of every task and retains durable facts as it works.
Stop Building Microsoft Agent Framework Agents That Forget
Add persistent long-term memory to Microsoft Agent Framework agents with Hindsight. Plug in one context provider and every run recalls relevant memories and retains the conversation automatically. No MCP, no tools the model has to remember to call.
Staleness-Aware Memory: When Your Agent Should Verify Before It Trusts
Hindsight's consolidated memory (observations and mental models) is derived from raw facts, so it can lag behind new writes. Instead of silently serving a stale snapshot, Hindsight flags how far behind each layer is, and the reflect agent verifies against raw facts before trusting it.
Chat With Your Obsidian Vault: Grounded Answers That Cite Your Notes
Give your Obsidian vault an AI agent that actually knows your notes. The Hindsight plugin syncs your vault into a memory bank and adds a chat panel whose answers are grounded on your notes and cite the source, with your vault staying the single source of truth.
Gemini Spark Persistent Memory: Agent-Initiated Recall Over MCP
Add persistent long-term memory to Google's Gemini Spark assistant with Hindsight. No plugin host, no hooks. Spark calls Hindsight's recall and retain tools over MCP, with Hindsight Cloud or a self-hosted OAuth proxy.
Cursor Persistent Memory: One Bank for the Editor and the CLI
Two new Hindsight integrations give Cursor persistent long-term memory: one for the Cursor editor (with a workaround for the broken sessionStart additionalContext channel in Cursor 3.x) and one for Cursor CLI. Both can share the same memory bank.
Haystack Persistent Memory: Drop-In Tools and Auto-Recall for Any Agent
Add persistent long-term memory to any Haystack agent with Hindsight. Three Haystack Tools (retain, recall, reflect) plus an optional HindsightMemoryWrapper that injects memories before each turn and stores the transcript after.
Flowise Persistent Memory: Drop-In Tool Nodes for Any Chatflow
Add persistent long-term memory to any Flowise chatflow or agent with Hindsight. Three Tool nodes (Retain, Recall, Reflect) drop straight into a Conversational Agent and share one Hindsight API credential.
Cline Persistent Memory: Lifecycle Hooks Instead of MCP
Add persistent memory to Cline with Hindsight using lifecycle hooks. No MCP server, no model tool-calling required. Hooks deterministically recall context before each task and retain what happened after.
How oh-my-pi Built Persistent Codebase Memory on Hindsight
oh-my-pi — a 10k-star terminal coding agent — uses Hindsight as its long-term memory backend. Here's a walkthrough of the integration: bank scoping, mental-model seeding, and the auto-retain pipeline, with code straight from the repo.
How Hindsight Learns: A Deep Dive Into Mental Models
Mental models are the top tier of Hindsight's learning hierarchy — persistent, self-refreshing understandings of the topics your agent asks about every session. A walkthrough from the schema up.
Long-Term Memory for Google ADK Agents with Hindsight
Add persistent long-term memory to Google ADK agents with Hindsight. Drop-in BaseMemoryService for automatic retain on session end and recall on search_memory — plus explicit retain/recall/reflect tools when you want them.
Voice Agents That Remember: Adding Memory to Vapi with Hindsight
Add persistent long-term memory to Vapi voice AI calls with one webhook. Recall caller history at call start, retain the transcript at call end — no per-turn integration needed.
Using Entity Labels to Automatically Tag Memories in Hindsight
Hindsight's entity labels turn free-text memories into structured, filterable classifications — automatically. A controlled vocabulary, four label types, and one tag: true switch that turns labels into filterable tags.
Hermes Agent on Windows: Set Up Persistent Memory with Hindsight
Nous Research just shipped Hermes Agent native on Windows. Here's how to give it persistent memory with Hindsight — one command, three modes, no Docker or WSL.
Building a Hermes Coding Assistant on Windows That Remembers Your Codebase
Nous Research just announced Hermes Agent native on Windows. Here's how to add persistent codebase memory with Hindsight — no Docker, no WSL, PowerShell start to finish.
Building an OpenClaw Coding Agent That Remembers Your Codebase
OpenClaw with Hindsight remembers your codebase across sessions — conventions, past bugs, architectural decisions. Setup in 2 minutes.
Adding Persistent Memory to Paperclip Agents with Hindsight
Give every Paperclip agent long-term memory with one plugin install. Agents recall context before runs and retain learnings after, no code changes needed.
Building a Hermes Coding Assistant That Remembers Your Codebase
Hermes Agent with Hindsight remembers your codebase across sessions, conventions, past bugs, architectural decisions. Setup in 2 minutes.
The Consolidation Problem in Agent Memory
Agents that remember everything remember nothing useful. A four-lever framework — importance, merge, decay, eviction — for consolidating agent memory.
Onboarding a New Engineer Onto Five Months of OpenCode Memory
A new engineer joins a codebase the team has been working in for five months. With OpenCode + Hindsight, day one looks very different from the README.
The Case Against External Vector DBs for Agent Memory
Most 'add memory to your agent' tutorials start with installing a vector database. They shouldn't. Why vector DBs are the wrong default for agent memory.
The Memory Layer Every n8n Workflow Was Missing
Hindsight's new community node adds persistent memory to any n8n workflow — Retain, Recall, Reflect. Workflows compound across runs instead of resetting.
Your Claude Code Subagents Don't Share What They Learn
Claude Code subagents (Plan, Explore, general-purpose, custom) each spawn fresh and discard everything they discover. Here's how to give them shared memory.
The Missing Layer in Every Agent Harness
Modern agent harnesses ship with tools, MCP, and IDE integrations — but no memory. Why that's the missing layer, and how harnesses are starting to fix it.
Multi-Turn Agent Memory with AWS AgentCore: Remember Across Sessions
Add persistent memory to AWS AgentCore agents with Hindsight. Agents remember context, decisions, and learnings across multi-turn conversations and sessions.
Agent Memory in SmolAgents: Retain, Recall, and Reflect
Add persistent memory to SmolAgents with Hindsight. Retain facts, recall context, and reflect on agent decisions across sessions.
Pipecat Voice AI Persistent Memory: Add Memory to Your Voice Pipeline
Add persistent long-term memory to Pipecat voice AI pipelines. Recall relevant past conversations and retain new exchanges with a single FrameProcessor between your user aggregator and LLM service.
Connect ChatGPT and Perplexity to Hindsight for Long-Term Memory
Use Hindsight's MCP integration to add persistent memory to ChatGPT and Perplexity. Store conversations, knowledge, and insights, then recall them across future sessions with OAuth-secured connections.
Your Agent Is Not Forgetful. It Was Never Given a Memory.
Why agents seem forgetful, and why memory is different from context windows and retrieval. How Hindsight adds long-term memory to agents.
Your OpenCode Agent Forgets Everything Between Sessions. Here's the Fix.
OpenCode sessions are stateless by default. The @vectorize-io/opencode-hindsight plugin adds persistent memory via automatic hooks and three explicit tools.
OpenAI Agents Forget Everything Between Runs. Here's the Fix.
OpenAI Agents SDK agents lose all state when a run ends. hindsight-openai-agents adds three tools and auto-injected memory instructions that give your agents persistent memory across sessions.
Your AI's Memory Is a Black Box. Constellation View Makes It Visible.
Constellation View and the Entity Co-occurrence Graph let you inspect the structure of a Hindsight bank as an interactive graph — debug memory quality, spot noisy hubs, and explain agent recall visually.
What's new in hindsight-openclaw 0.6
hindsight-openclaw 0.6 adds an interactive setup wizard, per-channel OpenClaw memory banks, an external API backend for shared persistent memory, and several reliability improvements.
How I Built Multi-User AI Memory into a Financial Product from Day One
A fintech co-founder shares how he integrated Hindsight into a financial AI system from the start, using self-hosted deployment and tag-based isolation for multi-user memory.
Your Agent Memory Setup Keeps Drifting. Hindsight 0.5.0 Adds a Templates Hub.
Hindsight 0.5.0 adds a Bank Templates Hub. Browse starter templates, import a manifest to configure any bank, and export setups to reuse across environments.
Agno Persistent Memory: Long-Term Memory for Agno Agents
Agno agents start each run fresh. hindsight-agno adds HindsightTools and memory_instructions so they can retain, recall, and reflect across sessions.
Adding Persistent Memory to OpenAI Codex with Hindsight
Give OpenAI Codex persistent memory across sessions with Hindsight. Auto-recall injects context before every prompt. Auto-retain extracts facts when sessions end.
One Memory for Every AI Tool I Use
How to wire Claude, ChatGPT, Claude Code, Codex, and OpenClaw to a single shared Hindsight memory bank using Cloudflare Workers as an OAuth 2.1 proxy.
Persistent Memory for AutoGen Agents with Hindsight
AutoGen agents lose all state when a session ends. hindsight-autogen adds three tools — retain, recall, reflect — that give your agents persistent memory across sessions.
Hindsight Is Now a Native Memory Provider in Hermes Agent
Hermes Agent now supports pluggable memory providers. Here's why Hindsight is the backend to use, and how to set it up in two minutes.
Hindsight Is #1 on BEAM — the Benchmark That Tests Memory at 10 Million Tokens
Hindsight is #1 on BEAM — the memory benchmark that tests at 10M tokens where context stuffing is impossible. See every published result and what drives the 58% margin.
Your OpenClaw Agents Are Strangers to Each Other. Hindsight Changes That.
When you run multiple OpenClaw instances, each one learns independently. Here's how to give every instance in your team a shared memory bank so what one learns, all know.
Teaching the Llama to Remember
LlamaIndex agents reset memory every session. Learn how to add persistent cross-session memory using hindsight-llamaindex in 3 steps. Full code examples included.
Why Your AWS Strands Agent Keeps Starting From Scratch (And How to Stop It)
AWS Strands agents start cold every session. hindsight-strands adds memory tools and loads relevant memories before the agent starts.
Adding Long-Term Memory to LangGraph and LangChain Agents
Learn how to add long-term memory to LangGraph and LangChain agents using three integration patterns — tools, nodes, and BaseStore — with per-user memory banks and semantic recall.
Agent Memory Benchmark: A Manifesto
Why we built Agent Memory Benchmark and made it fully open: a memory system should be judged on accuracy, speed, cost and ease of use together.
OpenClaude: Build a Claude Code Agent with Long-Term Memory — and Take It Everywhere
Run Claude Code on Telegram and connect it to Hindsight, so the agent you talk to from your phone remembers your past conversations.
Give the Only Self-Improving AI Agent (Hermes) a Memory Upgrade It Deserves
Swap Hermes Agent's file-based memory for Hindsight with one pip install. This plugin is now deprecated in favour of the Hermes plugin catalog.
I Built a Chatbot That Never Forgets — In 80 Lines of Python
Build a web chatbot in about 80 lines of Python with Streamlit and Hindsight. It remembers across restarts and shows what it knows in a sidebar.
How We Built Time-Aware Spreading Activation for Memory Graphs
How Hindsight answers questions about a period of time by walking from that window to the events around it, instead of just filtering by date.
Run Hindsight with Ollama: Local AI Memory, No API Keys Needed
Run Hindsight on your own machine with Ollama: no API keys, no cloud costs, and no data leaving your computer.
What's New in Hindsight Cloud: Document File Upload
Hindsight Cloud now takes PDFs, Word, PowerPoint, Excel, images and text files, and turns them into memories your agents can recall.
Pydantic AI Persistent Memory: Add It in 5 Lines of Code
Pydantic AI agents start from scratch on every run. hindsight-pydantic-ai adds long-term memory in five lines of Python.
How to Add Persistent Memory to OpenClaw with Hindsight
OpenClaw only remembers what the agent chooses to save. The Hindsight plugin saves every conversation and brings back the right context before each reply.
Give Your OpenAI App a Memory in 5 Minutes
Build a chatbot on the OpenAI SDK that remembers its users across restarts, using three Hindsight calls and no vector database.
The Open-Source MCP Memory Server Your AI Agent Is Missing
Run Hindsight with one Docker command and give any MCP client a memory it can store to, search, and reason over.
I Gave 100+ LLMs a Permanent Memory With One Python Package
hindsight-litellm gives any model behind LiteLLM a long-term memory: past context goes into each call, and each conversation is saved for next time.
Your CrewAI Agents Forget Everything Between Runs. Here's the Fix.
CrewAI crews lose what they learned when a run ends. hindsight-crewai keeps it across runs with three lines of setup.
Your Vercel Chat SDK bot forgets everything. Hindsight fixes that.
Chat SDK bots forget every message. One wrapper from @vectorize-io/hindsight-chat gives them memory that carries across Slack, Discord, Teams and Google Chat.